Research

911�� launches new Center for Satellite and Earth Science Research

Katarina Benson — Tue, 23 Jun 2026 21:34:41 +0000

911�� launches new Center for Satellite and Earth Science Research Katarina Benson Tue, 06/23/2026 - 17:34

At a recent gathering of air quality researchers from across the Washington, D.C., region and beyond, 911�� officially launched a new center that aims to advance Earth system science in atmospheric composition and air quality.

The Center for Satellite and Earth Science Research (CSER), based in 911��’s College of Science, will focus on delivering data-driven insights to support environmental resilience, improve public health outcomes, and inform decision-making at local, national, and global levels.

Daniel Tong, director of CESR. Photo by Evan Cantwell/Office of University Branding

“We are excited to establish a platform for researchers to work together,” said center director Daniel Tong, a professor in the J. Shukla Department of Atmospheric, Oceanic, and Earth Sciences. “By using the latest technology, including Earth system models, satellites, and artificial intelligence (AI), we can design and deploy better early warning systems for extreme weather events. Each year, thousands of people are killed by dust storms or wildfires. CSER is here to save these lives.”

In addition to Tong, the center’s leadership team includes Patrick Campbell, associate director for business development; Bok-Haeng “BH” Baek, associate director for research; Zafer Boybeyi, associate director for education; and Youhua Tang, chief scientist. Together, they will guide the center’s efforts to improve remote sensing, air quality modeling, and scientific workforce development.

“What’s most exciting is CSER’s potential to bridge research and real-world impact while training the next generation of scientists to work across disciplines and scales,” said Campbell.

The fourth annual Air Quality Research and Development Consortium (AIRDC) Workshop underscored the importance of collaboration across institutions and disciplines in tackling air quality challenges. The one-day event brought together scientists, modelers, and policy-focused experts to share emerging research and strengthen collaboration around some of the most urgent challenges in air quality and Earth system sciences.

As new technologies and analytical tools continue to evolve, researchers emphasized that partnerships like AIRDC and endeavors such as CSER will play a vital role in translating scientific advances into actionable solutions, which directly connects to university research efforts through the Grand Challenge Initiative and building a climate-resilient society.

“The greater Washington, D.C., area is like the Silicon Valley for atmospheric science,” Tong said. “We have thousands of scientists working on this topic in federal labs, universities, and industry.”

The Center for Satellite and Earth Science Research team. Photo by Evan Cantwell/Office of University Branding

Throughout the day, researchers from such institutions as Johns Hopkins University, George Washington University, University of Maryland, Howard University, American University, and University of Maryland Baltimore County shared new approaches to understanding air pollution sources, behavior, and impacts.

Collaborators from the Maryland Department of the Environment, DC Department of Energy and Environment, NOAA, DOE, and NASA also attended.

According to Campbell, what stood out the most was the strong integration of satellite observations, advanced monitoring and modeling, and AI-enabled data fusion. These technological improvements reflect both the field’s challenges and how rapidly it is moving toward unified, data-driven approaches.

“Collaborations like this one are so important because air quality challenges span climate, health, and environmental justice, making cross-institution collaboration essential to integrate expertise, accelerate innovation, and deliver real-world solutions,” said Campbell.

Topics

Research

College of Science

GCI-Climate

911�� research initiative examines subversive campaigns and prepares students for communication careers in new areas

sbrown79 — Tue, 23 Jun 2026 14:06:03 +0000

911�� research initiative examines subversive campaigns and prepares students for communication careers in new areas sbrown79 Tue, 06/23/2026 - 10:06

In This Story

Eric B. Shiraev

As debates over digital propaganda, misinformation, and media manipulation intensify, audiences are increasingly unsure what’s fact and what’s fiction across news outlets and social media feeds. At 911��, Sergei Samoilenko, associate professor in the Department of Communication,is working to better understand how digital disruption and manipulation practices shape public perception.

In 2016, Samoilenko, PhD Communication ’06, co-founded the Lab for Character Assassination and Reputation Protection (CARP), where he studies reputational attacks on individuals and organizations, and strategies to counter them. Samoilenko works alongside CARP co-founder Eric Shiraev, an adjunct faculty member at the Schar School of Policy and Government.

Samoilenko (bottom center) with his team, including CARP co-founder Eric Shiraev (right). Photo provided.

Through CARP, Samoilenko recently launched the Subversive Strategic Communication Research Initiative, examining how new era subversive campaigns disrupt conversations, hijack brands, and damage reputations through malicious actors ranging from trolls to angry activist groups that use boycotts, cancellation campaigns, and deepfakes to target brands and corporate executives.

The team is currently focusing on corporate subversive practices. The takeover of corporate identities is often intertwined with the hot-button issues present in public discourse that can be amplified by various agents of chaos and turned into social conflict situations. 

“We call them subversive because they aim to disrupt communication between brands and their stakeholders while subverting the original meaning, ideas, or identity of organizations,” Samoilenko said. “With new technologies emerging every day, artificial intelligence-generated deceptions and deepfakes are being created and spread at an alarming rate.”

By calling public attention to emerging malicious practices, the researchers hope this initiative will expose and combat these tactics—work that aligns with 911��’s broader commitment to strengthening peace, trust, and engagement in democracy, one of the six solutions in the university's Grand Challenge Initiative. 

The center’s research is a collaborative effort, but when it comes to understanding how online culture evolves, Samoilenko said students often have an advantage. “Students are leading the discussions because they’re digital natives. When it comes to platforms such as TikTok and Instagram, they’re more knowledgeable about subversive humor—memes, trends, scandals, and general news—and they see a lot of things that faculty don’t,” he said. “My job is to teach them how to synthesize that information and explain it from a theoretical standpoint.”

Valentina Fala. Photo provided.

One of CARP’s defining strengths is the student-centered approach. This model helped shape the careers of students and recent graduates. 

Alumna Valentina Fala, BA Communication ’25, transferred to 911�� from Northern Virginia Community College (NOVA) through the ADVANCE Program. Initially a CARP videography intern, Fala became a full-time media manager and intern supervisor. She credits that experience and Samoilenko’s mentorship with helping her secure her current role as communications coordinator at Spirit of America. 

“There's so much disinformation, and it’s important to be able to distinguish false narratives from the truth,” Fala said. “It’s one of the biggest challenges to democracy right now, and it’s essential to counter that with the truth.”

Fala helped organize CARP’s fifth international conference at Mason Square, featuring Michael LaRosa, former press secretary for former first lady Jill Biden.

“It was really impactful hearing his perspective and experiences on what he had to go through and manage with the media, and how women often face more character assassination attempts against their image,” Fala said.

Deirdre Prigge. Photo provided.

Deirdre Prigge, BA Communication ’23, MA ’24, also transferred from NOVA through ADVANCE and said she’s fascinated by the darker side of communication. 

“Deception is not just immoral communication, but it’s often used to achieve a certain goal,” Prigge said. “To understand how we're being persuaded, we must understand the ideological conflicts that our society is currently experiencing and how that gray area of communication works.”

Prigge, host of the CARP Radio podcast, credits 911��’s Summer Podcast and Radio Camp with Rodger Smith for preparing her for this role. 

“That's where I learned to edit audio in Audacity. Without Dr. Smith’s guidance, I wouldn’t have been nearly as knowledgeable when it comes to executing this podcast to spread the center’s work,” Prigge said.

After earning two degrees through 911��’s Bachelor’s to Accelerated Master’s Program, Prigge became an adjunct faculty member and CARP research affiliate. “I think a lot of people would like a very simple and easy flowchart of how they should respond in a moment of crisis,” she said. “Unfortunately, there is almost never one clear answer, but I believe that above all, authenticity is one of the most important values in communication.”

The center’s work continues to gain an international audience. CARP’s sixth conference, “Character Assassination in the Era of Permanent Crisis,” is scheduled for May 2027 at University of Piraeus in Greece.

Topics

College of Humanities and Social Sciences

Department of Communication

Alumni

Bachelor’s to Accelerated Master’s

ADVANCE

GCI-Democracy

Research

Your watch knows what you did last summer

Nathan Kahl — Mon, 15 Jun 2026 17:36:08 +0000

Your watch knows what you did last summer Nathan Kahl Mon, 06/15/2026 - 13:36

A smartwatch sitting quietly on someone’s wrist may seem unremarkable. But in a criminal investigation, that device could become a witness.

Umit Karabiyik. Photo provided

911�� Cyber Security Engineering Associate Professor Umit Karabiyik helps law enforcement agencies across the country understand how data from everyday connected devices can provide critical evidence in criminal cases. Through a U.S. Department of Justice (DOJ)–funded project, Karabiyik and researchers trained thousands of criminal justice professionals and provided technical assistance on cases involving everything from smartwatches and fitness trackers to smart home devices and medical technologies.

“We try to understand this Internet of Things (IoT) ecosystem and extract data from these technologies for evidentiary purposes in courts, criminal investigations, and criminal litigation,” said Karabiyik.

The project, funded by the Bureau of Justice Assistance, was first awarded in 2021 while Karabiyik was at Purdue University. Originally planned as a short-term effort, the grant was extended multiple times, allowing the team to continue responding to a growing challenge: helping investigators keep pace with the expansion of connected technologies in everyday life.

IoT devices include smartwatches, fitness trackers, smart appliances, home security systems, smart glasses, medical monitoring devices, and countless other products that collect and exchange data. “Law enforcement agencies need to understand what these technologies are, what the security issues are, what the privacy issues are, and most importantly, how to investigate them,” Karabiyik said.

Geolocation data points generated by an iPhone alongside data from nearby WiFi access points. Despite iPhone location services being disabled, information from surrounding devices is still collected. Image provided.

That work often goes beyond research papers and conference presentations. Since the project began, Karabiyik’s team has trained more than 7,000 criminal justice professionals through conferences, webinars, and specialized workshops. They have also become a resource for investigators facing technical questions in active cases.

“We get phone calls from law enforcement agencies that say, ‘I’ve got this case, and I got stuck. What do I do?’” Karabiyik said.

One line of research focused on how devices within Apple’s ecosystem communicate with one another. Karabiyik’s team discovered that Apple devices can collect identifying information about nearby Apple products even without direct interaction from users. The findings created new possibilities for investigators attempting to establish whether individuals or devices had been in proximity to one another.

After presenting the research, Karabiyik received inquiries from investigators working homicide and cold cases who wanted to know whether data from nearby Apple devices could help narrow the list of potential suspects. “These kinds of calls keep coming,” he said.

As part of the project, Karabiyik and colleagues serve as a criminal IoT helpdesk, of sorts.

In one case, Karabiyik served as an expert witness in a murder trial where investigators examined data from a smartwatch worn by the defendant, who maintained she had been asleep during the time prosecutors alleged the crime occurred.

“We looked at the technology and proved that she was indeed sleeping,” Karabiyik said. “There were no steps taken, and her stress level was perfectly fine until she found the victim dead.” The defendant was ultimately found not guilty.

While much of the project focuses on digital forensics, Karabiyik’s research also examines the privacy and security risks associated with connected devices. His team has built databases of vulnerabilities and studied how data collected by consumer technologies is stored, shared, and potentially exposed.

He noted that his research influences his own personal use. “I’m very picky about what technologies I use,” he said. He avoids devices with microphones and cameras whenever possible, does not use voice assistants such as Alexa or Google Home, and is cautious about products that collect large amounts of personal data.

At the same time, he sees enormous value in connected technologies when they are used responsibly. “Unless you are a bad person, these technologies can be super helpful,” he said. “If something happens to me, I know these devices are going to tell law enforcement a lot of things.”

As connected devices continue to multiply, Karabiyik expects demand for digital forensic expertise to grow as well. The current project concludes later this year, but he is already pursuing new DOJ funding opportunities aimed at helping forensic examiners, law enforcement agencies, and criminal justice professionals navigate an increasingly connected world.

Topics

Cybersecurity Research

Department of Cyber Security Engineering faculty

Internet of Things

Department of Justice

Research

Machine learning teaches asset traders not to sweat the small stuff

Katelynn C Hipolito — Mon, 15 Jun 2026 14:40:20 +0000

Machine learning teaches asset traders not to sweat the small stuff Katelynn C Hipolito Mon, 06/15/2026 - 10:40

Financial markets are governed by a combination of rational and irrational forces, statistical probabilities, and “animal spirits.” It takes fluency in both to understand the market, let alone to beat it. Yet market actors, including asset traders, now frequently use machine-learning techniques to help generate predictions of future asset prices.

Bo Hu, assistant professor of finance at the Costello College of Business at 911��. Photo provided by Bo Hu.

Scholars such as Bo Hu, assistant professor of finance at the Costello College of Business at 911��, are researching how these machine-learning tools are changing the decision-making processes that move the market, for better or worse.

The subject of Hu’s recent paper in Management Science is a well-known machine-learning technique called LASSO (least absolute shrinkage and selection operator), which has been widely adopted by financial practitioners since its introduction in 1996 by statistician Robert Tibshirani.

“If you look at the original paper, it describes an approach created by adding a regularization penalty to the least-squares regression method,” Hu says. Translation: “The power of LASSO is that it can screen out (i.e., penalize) weak signals while capturing stronger, potentially profitable ones. A LASSO-type trading strategy involves an ‘inactive zone’ for smaller-scale activity, in which the trading strategy is to do nothing.”

The paper was co-authored by Wen Chen of Texas Tech University and Liyan Yang of the University of Toronto.

Despite LASSO’s popularity and power, the soundness of its economic rationale remains unclear. Traders are presumably seeking any edge, however small, in the pursuit of outsized returns. How could it make sense for them to adopt a system designed to relegate signals of lesser magnitude to an ignored “inactive zone”?

To resolve this question, the researchers developed a theoretical framework to model a financial market in which multiple agents (read: traders) use an asset’s price history to forecast its return and make trading decisions.

In the benchmark case, when traders know the trading environment and do not face model uncertainty, they act according to an alternative to LASSO known as MSE (mean squared error). “MSE is essentially a Bayesian learning approach grounded in economic rationality,” Hu says. “It means that rational agents use Bayesian learning to update their beliefs and design their trading strategies. That stands in stark contrast to LASSO estimation, which filters out weak signals.”

However, the researchers found that when traders faced substantial ambiguity about the distribution of asset values, the trading calculus shifted. Ambiguity-averse agents will adopt a robust, LASSO-like strategy, refraining from trading in response to weak or intermediate market signals. With linear constraints imposed on the allowable trading strategies, the equilibrium decisions exactly matched LASSO estimates.

As an equilibrium trading strategy, LASSO can improve aggregate profits relative to the edge-seeking Bayesian alternative in the benchmark case, because the more conservative positions dictated by the “inactive zone” soften competition among traders. In a large market, aggressive competition drives the aggregate profits of traders using the conventional MSE strategy toward zero. By trading less aggressively, LASSO traders may preserve positive aggregate profits—a mechanism the researchers describe as “implicit collusion,” even though the traders do not communicate or explicitly coordinate.

However, Hu underscores that LASSO’s usefulness as a hedge against ambiguity depends on how well traders’ beliefs match the market’s true distribution of risk. The profitability of a LASSO strategy therefore hangs in the balance between traders’ biases and their enhanced market power (due to LASSO’s conservatism).

This balance is especially important when traders must distinguish between temporary fads and persistent trends. “Recently, the semiconductor index had a record-breaking run of consecutive gains. That’s very strong momentum, but if you are a contrarian, you might want to bet against that trend,” Hu says. “A trader must decide whether to follow the trend or take a contrarian position. LASSO’s inactive zone can help prevent overreaction to weak evidence, but it may also delay action when an emerging trend is genuine.”

There is also the possibility that a LASSO strategy could increase market volatility when combined with the other objectives and constraints of market makers, including high-frequency traders. “These traders need to control their inventory,” Hu says. “If they follow a LASSO-type strategy with an inactive zone, they will accommodate the liquidity demands of the market until their inventory reaches a certain threshold. At that point, they may start trading like momentum traders and cause the liquidity dry-up in financial markets. This dynamic is part of what fuels incidents like the ‘flash crash’ in 2010.”

In This Story

Bo Hu

Topics

Costello College of Business News

Costello College of Business Faculty Research

A.I. and Innovation - Costello

Costello Research Machine Learning

Costello Research Fintech

Finance - Costello

Costello Research Financial Crises

Costello Research Risk Management

Research

Artificial Intelligence

NSF CAREER award will support teen autonomy in age of AI

Nathan Kahl — Tue, 09 Jun 2026 15:45:38 +0000

NSF CAREER award will support teen autonomy in age of AI Nathan Kahl Tue, 06/09/2026 - 11:45

Adolescence has always been a time of figuring out who you are. Increasingly, that process unfolds alongside social media feeds, recommendation algorithms, and AI chatbots. 911��’s Nora McDonald received a prestigious National Science Foundation (NSF) CAREER award for $748,000 to better understand how adolescents experience and are shaped by these artificial intelligence (AI) and other personalized digital environments, and how they can develop the skills and capacities necessary to maintain their sense of self, autonomy, and agency within them.

McDonald, an assistant professor in the Department of Information Sciences and Technology, has spent several years studying a growing reality of adolescent life, and one increasingly shaped by personalized AI technologies. Her research has found that social media recommendation systems and AI chatbots can serve as spaces where young people reflect on themselves and seek feedback about who they are.

McDonald's work will give teens tools to properly engage with digital technologies. iStock photo.

“Much of the public conversation has been about how algorithms influence what kids see and how we go down rabbit holes,” McDonald said. “I’m interested in a different question: How do algorithms shape self-understanding and how do teens make sense of themselves in environments that are increasingly personalized and shaped by algorithms and AI?”

McDonald’s previous research suggests that even while teenagers often view AI chatbots and recommendation systems as practical tools, those systems can become important spaces for self-exploration and self-presentation.

“Over time, teens might come to expect these systems to reflect aspects of who they are,” McDonald said. “They use them not just for help with homework or entertainment, but also to explore and understand themselves.”

Those findings raise broader questions about adolescent development. If recommendation systems continually influence what young people see, what feedback they receive, and what content captures their attention, how will that affect how they see themselves?

Nora McDonalds. Photo provided

McDonalds's CAREER project will investigate that question through what she calls a resilience framework that examines how adolescents recognize, interpret, and respond to algorithmic influence and how it relates to the coherence of their sense of self.

The research combines interviews, diary studies, surveys, and participatory design activities to better understand how adolescents interpret and respond to algorithmic systems. McDonald will recruit teenagers from across the country, beginning with qualitative studies and eventually expanding to a national survey designed to generate broader statistical insights.

One major outcome of the project will be the development of practical resources and activities designed with teenagers to help them navigate personalized digital environments.

The effort differs from traditional digital literacy initiatives that focus primarily on explaining how algorithms work. “It helps them reflect on algorithmic influence and develop strategies that are really rooted in managing attention and maintaining perspective on who they are outside of digital experiences,” McDonald said.

The CAREER award also supports substantial educational activities. McDonald plans to develop a new undergraduate course focused on algorithmic self-defense from a human-computer interaction perspective. The project will also support a youth summer institute for high school students helping young people to critically engage with AI personalized digital technologies that increasingly shape their everyday experiences.

Learn about Artificial Intelligence at 911��

In This Story

Nora McDonald

Topics

information sciences and technology

social media intervention

Teens

Artificial Intelligence

Research

National Science Foundation

Is ‘gender gating’ the secret to success in online dating?

Katelynn C Hipolito — Tue, 09 Jun 2026 14:56:48 +0000

Is ‘gender gating’ the secret to success in online dating? Katelynn C Hipolito Tue, 06/09/2026 - 10:56

Digital matching platforms—from professional networking to ridesharing and accommodation services—add value by bringing supply and demand into balance. But deep-seated asymmetries can prove difficult to expunge, causing platforms’ functionality and productivity to suffer. This imbalance is common for many dual-matching platforms, including online dating services where men vastly outnumber women.

Sabari Rajan Karmegam, assistant professor of information systems and operations management.

The matrimonial matching platforms popular among people of Indian descent are a prime example, says Sabari Rajan Karmegam, assistant professor of information systems and operations management at the Costello College of Business at 911��. “The typical men-to-women ratio on these platforms ranges between 60:40 and 90:10,” he specifies.

In a forthcoming paper in Information Systems Research, Karmegam and co-authors Jui Ramaprasad of University of Maryland and Anand Gopal of Nanyang Technological University discuss the results of their experimental study examining engagement practices and outcomes for users seeking lifelong partners through a leading matrimonial platform in India.

As a result of the lopsided gender composition on the platform, men tended to send large numbers of invitations indiscriminately to increase their chances of finding a match. This resulted in a sizable skew in the number of invitations received by women: In Karmegam’s study, women received on average about 40 times as many expressions of interest (EIs) as men did.

The deluge of EIs left women feeling “extremely overwhelmed in the initial couple of days after joining the platform,” Karmegam says. “Once they were flooded with all these requests, it was hard for them to figure out what the platform was all about. Congestion led to reduced engagement by women and potential exit from the platform. Under prevailing social norms in India, families often share in that sorting burden.” The skewed design also left men dissatisfied with the platform due to the competition effect.

To improve the user experience for both parties, Karmegam and his co-authors tested the process of “gender gating,” which made women’s profiles visible only to men who meet culturally acceptable criteria for education, income, and age. For example, the “gender gate” prevented a man in his forties from viewing profiles of women more than 10 years younger or a couple of years older than he was. Women could override the “gender-gated” default settings with their own preferences, but men could not opt out of the restrictions.

The experimental design included two groups (one control and one treatment), each representing a state in India. The two states in the study were similar in size, socioeconomic indicators and located in close geographic proximity, but different in language and cultural characteristics. This minimized interference and helped isolate the effect of the intervention.

The researchers found that without negatively affecting male users, “gender gating” significantly improved women’s platform interaction, increased the number of matches, and improved match quality. It also resulted in women initiating more matches due to reduced screening time for finding a potential match.

Women in the treatment group received 6 percent fewer post-intervention EIs, compared to the control group, while the efficacy of the matches improved by 72 percent. The paper attributes this improvement both to the lower number of EIs received and to better alignment with social norms.

Women over 25, who sit at prime marriageable age and so align in age with more of the marriage-seeking men on the platform, experienced a 103 percent improvement in matching efficacy. They also sent 113 percent more EIs post-intervention, demonstrating increased agency.

In this case, a match is not a marriage but an open line of communication with a serious prospect. “Most of the conversation happens offline,” Karmegam says. “A lot of things need to happen outside the platform for things to work out, and our study does not capture that.”

Still, the “gender gating” experiment was such a success that the platform decided to extend the intervention across the entire user pool, Karmegam reports. In doing so, the platform joined other matchmaking services such as JDate and SKY People that use culturally appropriate criteria as a sorting mechanism to improve matchmaking accuracy.

Karmegam believes similar interventions could be used in non-romantic matchmaking scenarios. “This is something that can be applied to any people-to-people matching. For example, the majority of Uber drivers are men. Parents could ask for their daughter’s Uber teen account to be ‘gender gated’, as an extra layer of protection,” he says.

Hiring in competitive fields such as academia could also benefit from criteria-based sorting. “Narrowing the search to candidates who meet specific criteria, such as schools from which the applicants might have received their PhD degrees, would help raise the effectiveness of the process,” Karmegam says.

In This Story

Sabari Rajan Karmegam

Topics

Costello College of Business Faculty Research

A.I. and Innovation - Costello

Costello Research Data Analytics

Costello Research Digital Platforms

Costello Research Diversity

Costello College of Business News

Research

911�� engineering team uses robotics to rethink accessibility

Katarina Benson — Tue, 09 Jun 2026 13:58:00 +0000

911�� engineering team uses robotics to rethink accessibility Katarina Benson Tue, 06/09/2026 - 09:58

Many accessibility surveys depend on manual measurements, handwritten notes, and extensive walkthroughs with compliance checklists. A team of 911�� engineering students wondered if a robot could do it faster. Nine months later, they created one.

The project, called Salus, combines robotics, LiDAR technology, object detection, GPS mapping, cloud-based analytics, and a custom-built website to help survey public spaces for potential ADA accessibility barriers. Developed as part of a College of Engineering and Computing senior capstone project by mechanical engineering majors Lexi Chivers, Connie Lam, Mariah Tammera, Noemi Umanzor, and Tyler Yared, the system is designed to automate portions of the accessibility surveying process while allowing engineers and designers to better understand how people with disabilities experience physical spaces.

The Salus team with the robotic accessibility surveying system they developed as part of their senior capstone project at 911��. Photo provided

Salus was one of several 911�� capstone projects supported through a GO Virginia-funded initiative led by the Nexus234 Innovation District, which pairs students with industry-informed challenges and mentors.

“We saw a system that was operating poorly, and we wanted to optimize it,” said Chivers, the team lead.

The idea originated when one of Chivers’ teammates attended a conference and discussed the difficulties of collecting large volumes of survey data in the field with industry professionals.

“They basically said, ‘We wish we had something we could send out to collect data and not have to constantly manage,’” said Chivers. “That conversation sparked everything.”

The project consumed most of the team’s weekends as they worked through testing, software integration, fabrication, and constant iteration.

“A lot of people told us we weren’t going to be able to do this in nine months,” said Chivers. “At one point, someone told us it would take two years and eight NASA engineers.”

Instead, the students delivered a working proof of concept before graduation.

As the robot moves through a space, it uses LiDAR sensors, GPS mapping, and onboard cameras to identify and document potential accessibility issues. The data is processed through cloud-based systems and displayed through an interactive website. Rather than sorting through raw data, users can explore flagged locations through an interactive visual map built by the team.

For Chivers, the project also had a personal connection. She said her mother’s job teaching students with disabilities influenced the team’s conversations around accessibility and inclusion. “Just because something legally meets ADA standards doesn’t always mean it’s truly accessible for those with disabilities,” she said.

Kenan Aden, COO of Didlake and the team’s industry mentor, was introduced to the student team through Nexus234. He said the project impressed him both from its technical complexity and for the problem it set out to tackle.

“The entire team approached this project with an incredible level of determination and systems thinking,” said Aden. “What makes it especially meaningful is that they never lost sight of the people this technology is intended to help.”

"This team’s focus and dedication have been extremely impressive," said Leigh McCue, professor and chair of 911��’s Department of Mechanical Engineering. "Any time I popped my head into the senior design space, or walked visitors through for a tour, the team was hard at work and eager to showcase their technology."

One of the most rewarding parts of the experience for Chivers was discovering the kind of engineer she wants to become.

“I thought I wanted to stay in the background,” said Chivers. “But this project made me realize I really love being a leader, solving problems, and doing things that actually matter to people.”

Currently, the students are working with 911��’s Office of Technology Transfer to explore patent protection for the project’s intellectual property. Although the team is still deciding what comes next, Chivers said the technology has potential beyond the capstone project itself, including with construction firms, municipalities, designers, and accessibility planners.

In her advice to other entrepreneurs, Chivers said, “Your dreams are never too big. You just haven’t found all the tools you need to make them happen yet.”

Learn about Research at 911��

Topics

College of Engineering and Computing

Timing the perfect hardware hack

tdonnel — Tue, 09 Jun 2026 13:35:43 +0000

Timing the perfect hardware hack tdonnel Tue, 06/09/2026 - 09:35

Roombas have become a familiar part of everyday life, quietly navigating living rooms and kitchens. But behind that convenience is a complex system of sensors, algorithms, and data processing—and, as a group of 911�� cyber security engineering (CYSE) students—Finn Schaefer, Ryan Lam, Sidarth Kumar, Jimmy Tram, and Neil Sharma—discovered, a surprising vulnerability. Their capstone project research was accepted for presentation at one of the most prestigious venues for hardware-based security research, the IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

“It just scans the room, goes around, and starts mapping," said Finn Schaefer, comparing the vacuum cleaner to the robot at the center of his team's project.

These autonomous systems rely on technologies like LiDAR and SLAM (simultaneous localization and mapping) to build a virtual map of their environment and navigate safely. However, that same reliance on sensor data also opens the door to cyberattacks that can alter a robot’s perception, sometimes with dramatic consequences.

From left to right: Finn Schaefer, Neil Sharma, Ryan Lam, Sidarth Kumar, and Jimmy Tram. Photo provided.

The capstone project, advised by Assistant Professor Tanvir Arafin, challenged students to explore exactly that risk. From the outset, Arafin encouraged an open-ended, research-driven approach.

“Professor Arafin basically told us to try to break ROS, a robot operating system,” Schaefer said.

The assignment functioned as a “red-team” exercise, pushing students to think like attackers to understand vulnerabilities in autonomous systems.

The team’s early ideas focused on overwhelming the robot with false data, effectively flooding it with noise. But this proved too obvious. That initial concept “was really simple and easy to detect,” said Ryan Lam. A more subtle approach would be needed to create a meaningful, realistic attack.

Their breakthrough came in the form of a timing-based method that mimicked the robot’s normal operating patterns. Instead of bombarding the system, they carefully injected altered sensor data at precisely the right intervals.

“We eventually got to our more elegant solution, where we’re able to match the timing pattern that the robot actually expects,” Schaefer said. Because the manipulated data looked plausible and arrived in the expected cadence, the robot accepted it as real.

A judge examines the team's robot at the CYSE senior design event. Photo by Teresa Donnellan/CEC

The effect was striking: the robot’s internal map gradually diverged from reality. Even small manipulations could cause significant errors.

“With 2- to 5-percent drift, it would crash into walls,” Schaefer said.

In some cases, the system could be tricked into perceiving obstacles that didn’t exist. “It would see a wall that’s not actually there,” he added.

The team also demonstrated the ability to shrink or expand the robot’s perceived environment, causing navigation failures.

To prove the effectiveness of their approach, the students combined simulated analysis with real-world testing. They compared baseline maps to manipulated ones over time and observed the robot attempting to navigate using corrupted data.

“These comparisons served as the proof that we used to say that this works,” said team member Sidarth Kumar.

Additional testing showed that the attack remained effective even under network congestion.

This capstone project reflects Arafin’s broader work to secure the next generation of mobility systems, from connected vehicles to robotics. Moreover, the students came away with a deeper understanding of the emerging field of hardware security.

Tanvir Arafin (center) with the 2026 senior capstone teams he advised. Photo provided.

“This is an exceptional accomplishment and a testament to the curriculum rigor of the Cyber Security Engineering Department, reinforcing a tradition of excellence in undergraduate research at CYSE,” said Arafin. “Over the last few years, CYSE undergraduate students from our group have earned recognition at multiple national and international venues in transportation and autonomous systems security, notably the best demo award in the 18th Association for Computing Machinery Conference on Security and Privacy in Wireless and Mobile Networks and the first, second, and third places at the National Transportation Cybersecurity Competition. All of these accomplishments highlights both the students’ dedication and the strength of undergraduate research within our CYSE Department.”

In an era where autonomous systems are becoming increasingly common, from household robots to self-driving cars, the team’s work underscores a critical lesson: If a machine’s understanding of the world can be manipulated, so can its behavior. What seems like a harmless household device may, under the hood, share the same vulnerabilities as far more complex systems. And as these students demonstrated, understanding those vulnerabilities is the first step toward securing the future of autonomous technology.

Discover more Research at 911��

Learn more about the College of Engineering and Computing

In This Story

Tanvir Arafin

Topics

Cybersecurity Research

Senior Capstone Project

Undergraduate Research

Research

College of Engineering and Computing

competitions

Students

Why did the AI agent cross the road?

tdonnel — Mon, 08 Jun 2026 18:31:17 +0000

Why did the AI agent cross the road? tdonnel Mon, 06/08/2026 - 14:31

Workshopping, an iterative process where creators share ideas, test what works, and refine what doesn’t through collective feedback, is at the heart of any writers’ group. This collaborative dynamic inspired 911�� PhD students Shiwei Hong to explore whether artificial intelligence (AI) could benefit from a similar approach.

Hong developed a novel multi-agent system that simulates a collaborative comedy writing environment in which AI agents generate, critique, and refine humorous content together. Her research, recently accepted to the prestigious 64th Annual Meeting of the Association for Computational Linguistics, investigates how structured interaction among AI agents can improve creative output.

Shiwei Hong. Photo provided.

Humor remains challenging for artificial intelligence. “Generating a joke or something that is very funny is actually a very tricky question, because it requires a lot of how humans interpret the generated piece,” said Hong, who is working on a degree in computer science.

She created a “sandbox” environment to mirror real-world creative collaboration, populated by 35 AI agents assigned distinct roles and personalities powered by GPT-4.

“Five agents acted as performers. The rest acted as critics or audience members,” said Hong.

Designing 35 unique agent personas required imagination as well as technical expertise. Drawing on her interest in writing fiction, Hong created characters with varied social and cultural backgrounds, adding depth to the simulated interactions.

In one experimental environment, the performer agents generated two scripts in sequence without feedback; in another, they engaged the audience members in critique and discussion between the rounds of generation. The difference was significant.

Human evaluators compared outputs across multiple criteria, such as humor, coherence, and social tone. In more than 70 percent of cases, evaluators preferred scripts produced in the second round of the discussion-based environment.

The improvement appears to stem from collective learning. As agents interact, they build on shared insights, identifying patterns in audience preferences and refining their outputs accordingly. Technically, this process is supported by a shared conversational memory stored in a vector database, allowing agents to retrieve relevant past exchanges and incorporate them into new content. The result is an iterative, emergent form of creativity that begins to resemble human collaboration.

Looking ahead, Hong and her advisor, Assistant Professor Zhicong Lu, aim to expand the system by incorporating human participants and richer modes of interaction. Future directions include integrating voice, gestures, and immersive technologies such as virtual and augmented reality to better capture the nuances of live performance.

“In real comedy, we have faces, gestures, and real voices,” she said. “We hope to bring more of that into the system.”

By demonstrating that workshopping can significantly enhance machine-generated humor, Hong’s work suggests the future of artificial intelligence may lie not only in more advanced individual models, but also in communities of agents learning, creating, and perhaps even laughing together.

Overview of Multi-Agent Comedy Club. Credit: arXiv (2026). DOI: 10.48550/arxiv.2602.14770

Learn about Artificial Intelligence at 911��

Explore Research at 911��

Topics

Human Computer Interaction

computer science

College of Engineering and Computing

Artificial Intelligence

doctoral students

Research

911�� professor probes ‘Labubu economics’

Katelynn C Hipolito — Tue, 02 Jun 2026 15:03:55 +0000

911�� professor probes ‘Labubu economics’ Katelynn C Hipolito Tue, 06/02/2026 - 11:03

The billion-dollar Labubu phenomenon broke a cardinal rule of retail: Consumers need to know what they’re buying before they open their wallet. Most new Labubu sales took the form of “blind boxes,” where purchasers found out which type of doll they’d purchased only after the fact.

Zhechao Yang, assistant professor of information systems and operations management at Costello College of Business at 911��. Photo by Jeffrey Porovich/Costello College of Business.

Zhechao Yang, assistant professor of information systems and operations management at the Costello College of Business at 911��, says that the “blind box” strategy, or “probabilistic selling” in academic terminology, is a rapidly growing global phenomenon that goes way beyond Labubu. Her recently published paper in Manufacturing & Service Operations Management examines how, and why, this emerging strategy has worked for toymakers, car rental companies and booksellers alike—while delighting customers willing to pay for a surprise.

The paper was co-authored by Hongseok Jang of Tulane University and Xiajun Amy Pan of University of Florida.

The researchers used game-theoretic modeling to analyze the interactions of suppliers, retailers and customers in a market where a manufacturer sells through a retailer. In this realistic setup, a supplier offers an assortment of products ranging from high- to low-quality at wholesale prices, which retailers seek to sell to consumers at the highest possible profit. Either the retailer or the supplier can choose to initiate probabilistic selling (PS), selecting some mixture of high- and low-quality products to go in the “blind boxes.”

Yang and her co-authors noted that PS can improve profits for retailers and suppliers in a number of ways. “One is the market expansion effect,” Yang explains. “If there is an excess of high-quality products that consumers are not buying, they can be combined with low-quality products to form a new product, via PS…Another way is through strategic differentiation, essentially preventing the excess high-quality products from experiencing price convergence with lower-quality products.”

But PS’ profitability potential is far from uniform. As the paper clarifies, it can vary greatly with the context, based particularly on two elements: whether PS is retailer- or supplier-led, and whether high-value products are abundant or scarce.

The researchers found that transaction costs—the extra costs of creating and selling blind boxes—were one of the main determining factors. Whichever party initiates PS will have to bear certain costs, which may include the labor required to assemble “blind boxes,” and additional fulfillment, inventory and logistics costs. Additionally, Yang says, “There could be financial and accounting costs associated with adding new products.”

When retailers take it upon themselves to introduce PS, the associated transaction costs can reshape upstream pricing. Anticipating those costs, the supplier may lower the wholesale price of high-quality products to make the blind-box strategy viable for the retailer. This can help the retailer, but it also reduces the supplier’s margin and may make retailer-led PS unattractive to the supplier under some conditions.

When retailers take the lead, they will adjust the product mix for PS based on balancing transaction costs against the likelihood of product cannibalization—a trade-off that may give rise to more shortsighted choices.

On the other hand, supplier-led PS gives the supplier more control over both the blind-box mix and the wholesale terms. Also, by adjusting the number of high-quality products that will go in the “blind boxes,” the supplier can maximize price differentiation, thus increasing profits.

“When the supplier leads the strategy, it can reduce the channel inefficiency,” Yang says. “In the model, the supplier can control both the product mix inside the blind box and the wholesale terms offered to the retailer. That can make it easier to manage cannibalization and preserve the value of high-quality products.”

The importance of supplier-led PS becomes especially clear when high-value products are scarce. In that setting, the paper shows that firms should use the limited high-value capacity on “blind boxes” rather than sell those products separately.

Thus, the paper concludes that supplier-led PS, unlike the retailer-led variety, can create a “win-win-win” scenario where the supplier and retailer both earn higher profits, market coverage expands, and consumers benefit from access to a broader set of purchasing options.

However, power plays a significant role in real-world decisions around PS. “In reality, major retailers like Amazon may have more bargaining power, more pricing power. The high-level assumption we give this model is that when the retailer is more powerful, the retailer gets the first opportunity to decide whether to introduce PS., but that doesn’t mean it’s the best option for the whole supply chain,” Yang says.

“It’s better for the two parties to have some conversation before deciding who will take the power at the very beginning. Large retailers may have some advantages, but sometimes it’s better to give this power to the supplier.”

In This Story

Zhechao Yang

Topics

Operations - Costello

Costello Research Retail

Costello Research Business Model Innovation

Costello College of Business News

ISOM Faculty Research

Costello College of Business Faculty Research

Research

Research

911�� launches new Center for Satellite and Earth Science Research

Topics

911�� research initiative examines subversive campaigns and prepares students for communication careers in new areas

In This Story

Topics

Your watch knows what you did last summer

Topics

Machine learning teaches asset traders not to sweat the small stuff

In This Story

Topics

NSF CAREER award will support teen autonomy in age of AI

Related Stories

In This Story

Topics

Is ‘gender gating’ the secret to success in online dating?

In This Story

Topics

911�� engineering team uses robotics to rethink accessibility

Related Stories

Topics

Timing the perfect hardware hack

Related Stories

In This Story

Topics

Why did the AI agent cross the road?

Related Stories

Topics

911�� professor probes ‘Labubu economics’

In This Story

Topics

Research

911���� launches new Center for Satellite and Earth Science Research

Topics

911���� research initiative examines subversive campaigns and prepares students for communication careers in new areas

In This Story

Topics

Your watch knows what you did last summer

Topics

Machine learning teaches asset traders not to sweat the small stuff

In This Story

Topics

NSF CAREER award will support teen autonomy in age of AI

Related Stories

In This Story

Topics

Is ‘gender gating’ the secret to success in online dating?

In This Story

Topics

911���� engineering team uses robotics to rethink accessibility

Related Stories

Topics

Timing the perfect hardware hack

Related Stories

In This Story

Topics

Why did the AI agent cross the road?

Related Stories

Topics

911���� professor probes ‘Labubu economics’

In This Story

Topics

911�� launches new Center for Satellite and Earth Science Research

911�� research initiative examines subversive campaigns and prepares students for communication careers in new areas

911�� engineering team uses robotics to rethink accessibility

911�� professor probes ‘Labubu economics’