computer science

Anonymity’s ARX nemesis

Nathan Kahl — Mon, 20 Oct 2025 15:12:08 +0000

Anonymity’s ARX nemesis Nathan Kahl Mon, 10/20/2025 - 11:12

A team of faculty and students from �鶹��Ƶ recently discovered a vulnerability in a widely used anonymization tool. They presented their findings last week in Taiwan at the Association for Computing Machinery Conference on Computer and Communications Security (ACM CCS), one of the world’s most prestigious computer security conferences, with a very low paper acceptance rate.

The problem they discovered was with ARX, an open-source data anonymization tool, which provides what is referred to as k-anonymity. It is a commonly used tool in clinical settings to maintain data privacy. The discovery is particularly important at a time when more and more private data is being used in a variety settings and systems.

Evgenios Kornaropoulos, an assistant professor in the Department of Computer Science, said, “Sometimes this type of microdata is very valuable. Tools like ARX anonymize the data so it’s compliant with HIPAA, and then that data can be shared with policymakers, engineers, scientists, and others who will make policy decisions and scientific studies based on this information.”

While many people receiving medical care are comfortable with their information being included in larger data sets for purposes of medical discovery, they likely do not want personal, identifiable information released.

“For patients, and especially those from more vulnerable or marginalized communities, data privacy is not an abstract concern, it’s deeply tied to trust in the health care system," said paper co-author Rebecca Sutter, a professor in the School of Nursing, and director of the MAP Clinics. "The integrity of tools like ARX matters because they underpin how we protect patient information while advancing public health research. When anonymization fails, it’s not only a technical vulnerability, it’s a human one."

Computer science PhD student Somiya Chhillar, lead author on the paper, said that the ubiquity of ARX was a reason they chose to study it. “We wanted to see how ARX really operates and how the algorithm works. While we were doing that, we realized that a few of the steps that it takes are very opportunistic, and because of that, it leaks information that we shouldn't be finding out by just looking at the anonymized data.”

Chhillar said that ARX follows a “greedy strategy,” explaining that there is a tension between privacy and utility. When data is shared, it should be useful without leaking information. The best metric for deciding the data usefulness is measured by information loss while the data is being made private. “The algorithm tries to minimize information loss while anonymizing the data, and ideally, we want the least possible information loss. And that's the greedy aspect of it; it's not always going for the most private, it’s just going for the most utility.”

This is what backfires, said Kornaropoulos, because experts (or attackers) can reverse engineer the anonymization steps the algorithm took throughout its execution to maximize utility and figure out properties of the data that were there before and after this anonymization step.

Kornaropoulos praised his student’s dedication to the discovery, noting that Chhillar “worked on this project for a while, and this code base of ARX is an elaborate tool, with thousands of lines of code. She had to go through it to truly internalize understand everything that's going on there,” he said.

The project was supported by a Commonwealth Cyber Initiative (CCI) grant from the program, “Securing Interactions between Humans and Machines,” and as a requirement of the grant, the project crossed different parts of the university. The College of Engineering and Computing collaborated with �鶹��Ƶ and Partners (MAP) Clinics, which provided the data.

In This Story

Evgenios Kornaropoulos

Rebecca Sutter, DNP, APRN, BC-FNP

Learn more about Cybersecurity at George �鶹��Ƶ

Topics

computer science

Cyber Security

Data Mining in Health Care

Commonwealth Cyber Initiative (CCI)

Research

Bluetooth blues? George �鶹��Ƶ turns a bug into a big win

Nathan Kahl — Thu, 21 Aug 2025 01:28:32 +0000

Bluetooth blues? George �鶹��Ƶ turns a bug into a big win Nathan Kahl Wed, 08/20/2025 - 21:28

�鶹��Ƶ College of Engineering and Computing faculty members made a significant impact at the 2025 USENIX Security Conference, in Seattle, including winning the Distinguished Artifact Award.

Photo provided

“Tracking You from a Thousand Miles Away! Turning a Bluetooth Device into an Apple AirTag Without Root Privileges,” a paper by the Department of Computer Science’s PhD student Junming Chen, PhD candidate Xiaoyue Ma, and Lannan Luo and Qiang Zeng, both associate professors, won the prestigious Distinguished Artifact Award, which was granted to only six of the 2,385 submitted papers.

Their research demonstrated how to turn Bluetooth devices into a trackable "AirTags" without requiring root privileges. The research revealed a vulnerability in Apple's Find My Network that can leverage more than a billion active Apple devices as unwitting finders. The high-quality artifact with its complete documentation and practical implementation provides researchers with an invaluable toolkit for evaluating tracking vulnerabilities in crowd-sourced location networks. Their work was previously reported by the university and received media attention in various outlets.

A crowd gathers at the team's poster session. Photo provided.

USENIX Security is one of the country’s premier cybersecurity conferences, and this year received 2,385 paper submissions with a 17% acceptance rate. The following George �鶹��Ƶ research papers were also accepted at USENIX this year. 

Rowhammer-Based Trojan Injection: One Bit Flip Is Sufficient for Backdooring DNNs
Xiang Li, Ying Meng, Junming Chen, Lannan Luo, and Qiang Zeng, �鶹��Ƶ

DISPATCH: Unraveling Security Patches from Entangled Code Changes
Shiyu Sun and Yunlong Xing, �鶹��Ƶ; Xinda Wang, University of Texas at Dallas; Shu Wang, Palo Alto Networks, Inc.; Qi Li, Tsinghua University; Kun Sun, �鶹��Ƶ

TYPEPULSE: Detecting Type Confusion Bugs in Rust Programs
Hung-Mao Chen and Xu He, �鶹��Ƶ; Shu Wang, �鶹��Ƶ and Palo Alto Networks Inc.; Xiaokuan Zhang and Kun Sun, �鶹��Ƶ

LLMmap: Fingerprinting for Large Language Models
Dario Pasquini, RSAC Labs; Evgenios M. Kornaropoulos and Giuseppe Ateniese, �鶹��Ƶ

Explore the College of Engineering and Computing

In This Story

Qiang Zeng

Topics

AI’s blind spots, one PhD student’s clear vision

Ryley McGinnis — Mon, 11 Aug 2025 18:36:42 +0000

AI’s blind spots, one PhD student’s clear vision Ryley McGinnis Mon, 08/11/2025 - 14:36

When artificial intelligence makes a mistake, the consequences can be annoying—or they can be life-altering. For one �鶹��Ƶ computer science PhD student, the stakes are clear: biased algorithms in health care aren’t just a technical flaw, they’re a human risk. And with internship experience teaching him crucial skills beyond the classroom, Fardin Ahsan Sakib is ready to make a difference in health care.

Sakib’s research in natural language processing (NLP) addresses concerns that many may have when working with emerging large language models (LLMs), but when it is applied to health decisions, there could be deeper negative risks. Tools like ChatGPT pull from vast amounts of information, but they have sometimes been known to “hallucinate,” or make up information.

“Sometimes these systems are taking a shortcut to get you an answer,” said Sakib. “But regardless of where it comes from, it can provide you incorrect information.” And in the health care space, these LLMs could aid doctors, but not when they could be driving improper care.

In electronic health records (EHRs), patients’ diagnoses, medical history, and demographic data are stored and organized. This information includes social determinants of health, like employment status, family situations, or housing conditions, hidden in records.

Fardin Ahsan Sakib is seeking to bring accurate and reliable large language models' capabilities to healthcare.

“These factors can affect up to 80% of health outcomes,” Sakib said. “So it's very important that we can extract them correctly from clinical notes and that the model is not introducing any bias.”

Sakib poses a scenario: A doctor is using an NLP tool to quickly assess a new patient’s health. The LLM is pulling from the patient’s records, and the physician asks the system, “Is this patient a smoker?” The system quickly sifts through the data, and says that yes, this patient is a smoker. The physician then proceeds to make care recommendations based on this information. Maybe they order a lung cancer screening, or they speak with the patient about smoking cessation resources.

But what if that answer was incorrect? The LLM decided to take a shortcut, because, based off the information it has, it discovered that most people with similar demographic data to the patient are indeed smokers, but this one isn’t.

“There are two things at play: bias and hallucination,” said Sakib. “First, algorithms can only use the information they have, and if that information is missing an entire racial or ethnic group, it can be biased. Second, these models can use this biased information to take shortcuts, leading to them delivering false information.”

Sakib isn't simply identifying these problems; he's developing solutions. His recent research on detecting and mitigating shortcut learning in health record processing was accepted for presentation at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), one of the premier NLP conferences.

That desire to build reliable and trustworthy NLP tools has driven Sakib’s academic work and his professional pursuits.

At Brillient Corporation, where he interned last summer, Sakib worked on creating a retrieval augmented generation system that connected an LLM to the Food and Drug Administration’s (FDA) knowledge base to make accessing and retrieving information faster and grounded in facts. He and his colleagues submitted a patent for this effort.

This summer, he's deep into another high-impact internship at Amazon. “Amazon wants to automate support so that when you ask for help, a large language model can try to solve the problem before handing it off to a human,” he said.

Despite the different settings, he sees clear continuity between his internships and academic work. “The industry experience helps me in my research, and my research experience helps in industry. It goes both ways,” he said. “In academia, collaboration is usually focused within a lab or research group. In industry, I’ve worked with engineers, product managers, and domain experts all at once, spanning from health regulators to AWS cloud architects. That diversity of perspectives changes how you solve problems, and I’ve brought that mindset back into my research collaborations.”

It’s that dual perspective—academic precision paired with industry scale—that he plans to take with him into industry after graduation.

“George �鶹��Ƶ has prepared me for a lot. From day one, all of the professors have helped me grow as a researcher, a person, and as a team member,” said Sakib.

More on AI Research at George �鶹��Ƶ

Topics

Artificial Intelligence

large language models

computer science

Long Nguyen and Kimmy Duong School of Computing

Students

internships

CEC students

One tiny flip that opens a backdoor in AI

Nathan Kahl — Mon, 11 Aug 2025 13:13:32 +0000

One tiny flip that opens a backdoor in AI Nathan Kahl Mon, 08/11/2025 - 09:13

A self-driving motor vehicle is cruising along, its numerous sensors and cameras telling it when to brake, change lanes, and make turns. The vehicle approaches a stop sign at a high rate of speed, but instead of stopping, it barrels through, causing an accident. The problem will probably never be found by investigators, but instead of reading the stop sign as a stop sign, the car had been hacked to see it instead as a speed limit sign.

According to research by �鶹��Ƶ’s Qiang Zeng, an associate professor in the Department of Computer Science, and PhD student Xiang Li and colleagues, it is remarkably simple for a would-be hacker to pull off such a feat.

“An attacker can selectively flip only one bit, and this changing of the bit from 0 to 1 allows an attacker to attach a patch onto any image and fool the AI system. Regardless of the original image input, that patched image will be interpreted as the attacker’s desired result,” said Zeng.

So, if the hacker wants an artificial intelligence (AI) system to see a stop sign as something else, or a cat as a dog, the effort is minimal. Consider a scene potentially pulled from a Mission: Impossible movie, where a corporate spy can pass himself off as a CEO, gaining access to sensitive information.

Zeng and colleagues presented a paper with the findings at USENIX Security 2025, one of the nation’s premier cybersecurity conferences.

AI systems have what’s called a deep neural network (DNN) as a key component. DNNs let AI handle complex data and perform many different tasks. They work by using numerical values, called weights, each typically stored in 32 bits. There are hundreds of billions of bits in a DNN, so changing only one is particularly stealthy, according to Zeng.

“Once the attacker knows the algorithm, then it can take literally only a couple minutes to make the change. And you won’t realize you’ve been attacked because the AI system will work as usual. Flipping one bit effectively sneaks a backdoor into AI, exploitable only by those who know the patch,” he said.

Prior work in this area typically added a patch tailored to the original image—for example, modifying a stop sign specifically so that it is misclassified as a 65 mph speed limit sign. This new research uses what’s called a uniform patch that works regardless of the original input; the hacker could cause the system to interpret various signs as a speed limit sign. This input-agnostic attack represents a newer and more dangerous threat.

When they began the project the researchers wanted to learn the minimum level of effort needed to launch such an attack, recognizing that flipping hundreds of bits is impractical and gets exponentially difficult. “It turned out, we only needed to flip one,” Zeng said with a laugh. The team named their attacking system, appropriately, OneFlip.

The researchers are now only looking at the implication for images, as image classifiers are among the most popular AI systems, though they suspect this hacking technique could also work for things like speech recognition. Zeng said that their success rate during testing was near 100% and stressed that all DNN systems are likely to be subject to such hacking.

This does not necessarily mean such hacking will run rampant. To launch the attack, Zeng said, there are two requirements: access to the exact weights (numerical values that the model learns during training of the AI system) and the ability to execute code on the machine hosting the model. For example, in cloud environments, attackers might exploit shared infrastructure where multiple tenants’ programs run on the same physical hardware.

Learn about AI at George �鶹��Ƶ

Topics

Cyber Security

Cyber Security Research

computer science

Autonomous Cars

Artificial Intelligence

Research

Barbara Snyder honored by National Academic Advising Association for excellence as an advising administrator

Lauren Reuscher — Tue, 29 Jul 2025 17:50:14 +0000

Barbara Snyder honored by National Academic Advising Association for excellence as an advising administrator Lauren Reuscher Tue, 07/29/2025 - 13:50

Two members of George �鶹��Ƶ's academic advising community were honored with regional awards from the National Academic Advising Association (NACADA) this spring. These awards recognize excellence in academic advising in NACADA Region 2, which includes Delaware, Washington, D.C., Maryland, New Jersey, Pennsylvania, and Virginia.

Barbara Snyder, director of student success and academic advising in the Costello College of Business, received the NACADA award for Excellence in Advising—Advising Administrator.

Barbara Snyder, BS Psychology ’08, director of student success and academic advising in the Costello College of Business, received the award for Excellence in Advising—Advising Administrator.

Joshua Fletcher, undergraduate academic advisor in the Computer Science Department, was honored with the award for Excellence in Advising—Primary Role Advisor. Read more about him.

Fletcher and Snyder were formally recognized at the NACADA Region 1 and 2 conference in April in Buffalo, New York.

Snyder will be a George �鶹��Ƶ student once again this fall, when she starts the doctoral program in Education with a concentration in Higher Education. Snyder earned a master’s in student personnel in higher education from the University of Florida.

We asked Snyder to share some insights her experiences in academic advising and what it means to be recognized for her work.

How long have you worked at George �鶹��Ƶ? How has your job changed over the years?

I began as an academic advisor in the Costello College of Business in 2011, then spent a few years at the University of Houston-Clear Lake, where I helped launch their first centralized advising center. I returned to George �鶹��Ƶ in 2017, and since then, I’ve become the director of student success and academic advising for the Costello College of Business.

Over the years, my roles have evolved from individual advising, to shaping strategy, training, and student success initiatives at the college level. Each phase of my career has reinforced my belief that academic advising is one of the most essential components of student success.

What are your main responsibilities in your role?

I work alongside a team of directors to oversee undergraduate academic advising for more than 4,500 business majors. I co-lead the strategic vision for the office and serve as the main coordinator of onboarding and training for all new advisors.

I also oversee pre-orientation advising, orientation programming, and student-centered initiatives like the Global Engagement Scholars Program and first-generation student programming. Additionally, I serve as Costello’s undergraduate advising liaison to the university’s Academic Advising Leadership Council, working with advising leaders from each college to create a consistent and collaborative advising experience across the university.

What do you like best about your job?

I love that my work allows me to impact both students and staff. Supporting advisors in their growth, watching students achieve milestones they once doubted were possible, and designing programs that help people feel a sense of belonging—those are the moments that keep me going.

Joshua Fletcher and Barbara Snyder were recognized for excellence in academic advising at the NACADA conference in April. Photo provided

You were recognized at the recent NACADA regional conference with their Excellence in Advising—Advising Administrator award. What are your biggest takeaways from their conferences?

I’ve attended both regional and annual NACADA conferences over the years. What I appreciate most is the sense of community and shared purpose. You are surrounded by professionals who deeply care about student success and who are generous in sharing tools, ideas, and lessons learned.

I enjoy catching up with colleagues I’ve worked with through the years and connecting with new advisors entering the field. I find a lot of value in both mentoring and being mentored; those relationships and exchanges of experience are some of the most energizing parts of the conference. Every time I attend, I come back inspired.

Do any memorable moments stand out in your academic advising experience?

One that stands out was leading a full virtual orientation and advising experience for more than 1,500 students during the pandemic. We had to pivot quickly, redesign everything, and still make students feel seen and supported. It was one of the most exhausting, yet rewarding, moments of my career.

I also carry with me the many memories of supporting academic advisors throughout their professional journeys, especially those who have gone on to become leaders across campus or at other institutions. Being part of their growth is incredibly meaningful and a big part of what keeps me passionate about this work.

Academic advising at George �鶹��Ƶ

Topics

Faculty and Staff News

Academic Advising

Costello College of Business

computer science

College of Engineering and Computing mourns the passing of Mark Pullen

Martha Bushong — Tue, 15 Jul 2025 14:51:30 +0000

College of Engineering and Computing mourns the passing of Mark Pullen Martha Bushong Tue, 07/15/2025 - 10:51

In This Story

J. Mark Pullen

The College of Engineering and Computing community is deeply saddened by the passing of Professor J. Mark Pullen, Director Emeritus of �鶹��Ƶ’s C5I Center. Mark served as director of the C5I Center from 2005 until his retirement in 2020 and was also a beloved professor of computer science at �鶹��Ƶ. Under his leadership, Mark maintained the center's growth and recognition as a leading institution for national and global research in C5I. Mark was also recognized as a pioneer in distance education, personally developing open-source synchronous Internet software to deliver online MS degree programs in computer science long before online learning became ubiquitous. This work demonstrated his forward-thinking approach and commitment to making high-quality education accessible to the right students in the right place at the right time.

Mark’s contributions are highlighted by his strong academic expertise, practical engineering skills, and internationally recognized operational and strategic insights. He skillfully balanced developing the nation’s security future workforce, teaching leading-edge courses in computer networking and networked virtual environments with knowledge and strong mentorship, while simultaneously leading developmental solutions for complex defense and cybersecurity problems.

Mark Pullen. Photo by Ron Aira, Creative Services.

His direct contributions significantly enhanced the interoperability of command-and-control systems through leading-edge modeling and simulation, personally leading efforts such as the “Extensible Modeling and Simulation Framework” (XMSF) and the “Command and Control – Simulation Interoperation” (C2SIM) initiatives, which have significantly influenced NATO and SISO standards still used worldwide. After retiring from George �鶹��Ƶ, Mark continued to “pay it forward” to the future of our nation’s security, as he was personally recruited to participate in advancing interoperability standards through his efforts working with NATO’s “Coalition Warrior Interoperability eXploration, eXperimentation, eXamination, eXercise” (CWIX) events.

Beyond his recognized technical expertise, Mark was a dedicated teacher, respected mentor, and valued colleague. His sustained commitment to problem-solving and supporting students and peers alike helped create the collaborative environment the C5I Center still benefits from today. Professor J. Mark Pullen, Director Emeritus, will be greatly missed, and his impact will continue through the focused efforts he started, the standards he helped develop, and the many people he guided throughout his career.

The tribute and obituary from Mark’s family are available here.

Instead of flowers, the family requests that memorial contributions be made to Shepherdstown Presbyterian Church at the address below, or shepherdstownpresbyterian.org, or to Coalfield development.org/community-based-revitalization-projects/

Service Information

Saturday, August 2, 2025, at 2:00 p.m.
Shepherdstown Presbyterian Church
100 W. Washington Street
Shepherdstown WV 25443

Topics

College of Engineering and Computing

School of Computing

computer science

Computer Science faculty

Faculty and Staff News

Advisors from George �鶹��Ƶ receive National Academic Advising Association honors

Lauren Reuscher — Thu, 29 May 2025 12:47:53 +0000

Advisors from George �鶹��Ƶ receive National Academic Advising Association honors Lauren Reuscher Thu, 05/29/2025 - 08:47

Joshua Fletcher, undergraduate academic advisor in the Computer Science Department, was honored with the award for Excellence in Advising—Primary Role Advisor.

Barbara Snyder, director of student success and academic advising in the Costello College of Business, received the award for Excellence in Advising—Advising Administrator.

Joshua Fletcher and Barbara Snyder were recognized for excellence in academic advising at the NACADA conference in April. Photo provided

Fletcher and Snyder were formally recognized at the NACADA Region 1 and 2 conference in April in Buffalo, New York.

Academic advisors serve as vital resources as students navigate their academic journeys at George �鶹��Ƶ. Delivering a distinctive and inclusive student experience is one of the university’s strategic priorities, and student advising is a critical part of the student services infrastructure.

Fletcher started working at George �鶹��Ƶ in 2019, after previously working as a school counselor at a Title I middle school in Pinellas Park, Florida. He earned a master’s degree in counseling education from the University of Florida. We asked him to share some insights into his experiences advising students at George �鶹��Ƶ and what it means to be recognized for his work.

What are your main responsibilities in your role? What types of students do you advise?

I advise approximately 2,600 undergraduate computer science and applied computer science students at all stages of their education journey. Academic advising has given me the opportunity to understand and evaluate students in difficult situations, develop a plan of action by utilizing the degree audit system, and take the lead in group advising sessions.

Joshua Fletcher is an undergraduate academic advisor in the Computer Science Department. Photo provided

I also process important documents such as substitutions, waivers, major declarations, re-enrollments, appeals, and many others. In addition, I help with several events throughout the year such as College of Engineering and Computing Visit Days, Fall/Spring Previews, orientations, Spotlight Days, and more.

What do you like best about your job?

I take an approach to meet students where they are. My philosophy on advising is to understand where the student is, but be real about the interworking of their major.

I have a dialogue with my students about their passion, hobbies, and goals. I use this information to help them build a support system for their career goals and encourage them to create alternative paths that will lead them to be successful in the future.

What are some of the biggest challenges in your role?

One of the challenges that advisors face is the caseload numbers. We see a lot of students every day, and it is not surprising that our appointments are booked.

Have you previously attended the NACADA conference? What do you enjoy most about the conference and the organization?

Last year, one of my colleagues and I attended the Regional 2 conference in New Jersey. One of the breakout sessions was called “How to Publish for NACADA,” and we discovered the opportunity to write for NACADA. Because we have so many personal experiences as advisors, we thought it would be a great idea to share some of our stories with other advisors.

To our surprise, our article was published in the September 2024 edition of Academic Advising Today. This is my first published article. Our article, “Academic Advisors' Mental Health Literacy and Experiences Working with Students Facing Emotional and Mental Health Issues,” encourages other advisors to gather information from research and colleagues to become more informed about how to effectively work with students who struggle with mental and emotional health issues.

What memorable moments stand out to you in your academic advising experiences?

The Degree Celebration for the College of Engineering and Computing. The Computer Science advising team always helps out with the event. One year, several of our students came up to us and thanked us for helping them through their journey at George �鶹��Ƶ.

Graduation is a time of celebrating the students’ success, but it also felt good to hear that we are appreciated by our students.

Academic advising at George �鶹��Ƶ

Topics

Faculty and Staff News

Academic Advising

College of Engineering and Computing

computer science

Costello College of Business

Tech Talent Investment Program (TTIP)

George �鶹��Ƶ’s ROARS lab retains its ranking as a leader in AI safety at the 2024 International Neural Network Verification Competition

Jennifer Pocock — Mon, 19 May 2025 20:47:30 +0000

George �鶹��Ƶ’s ROARS lab retains its ranking as a leader in AI safety at the 2024 International Neural Network Verification Competition Jennifer Pocock Mon, 05/19/2025 - 16:47

In This Story

ThanhVu Nguyen

The team’s NeuralSAT advanced the frontiers of trustworthy artificial intelligence, earning second place in a highly competitive field of international teams advancing the formal verification of AI systems.

Associate Professor ThanhVu Nguyen

NeuralSAT is an open-source verification tool developed by experts in Formal Methods/AI Hai Duong and ThanhVu Nguyen, both of �鶹��Ƶ. It analyzes whether deep neural networks behave as intended, even under adversarial or uncertain conditions. The International Neural Network Verification Competition (VNN-COMP) gathers international research teams working on formal methods for AI safety—methods that are increasingly important as neural networks are deployed in autonomous systems, healthcare, finance, and other mission-critical systems.

"Our goal with NeuralSAT is to bring precision and robustness to AI systems,” said Nguyen, an associate professor in computer science, “especially as they are increasingly used in safety-critical settings."

Hai Duong is a third-year PhD candidate

Each year, the participating VNN-COMP tools are evaluated across a wide set of benchmarks that test scalability, correctness, and performance. The 2024 competition’s results were recently released.

"This year’s benchmarks pushed the boundaries of what verification tools could handle—both in terms of scale and complexity," said Duong, a third-year computer science PhD candidate. "We’re proud that NeuralSAT remained among the top performers, showing strong results across both safety and robustness categories."

NeuralSAT was developed in close collaboration with researchers across multiple institutions, including the University of Virginia’s Matt Dwyer. It builds on recent advances in symbolic reasoning, SAT solving, and abstraction. In its inaugural appearance at VNN-COMP in 2023, NeuralSAT placed fourth overall and received the New Participant Award. In addition to competitions, the tool has been featured at top-tier conferences such as the Symposium on the Foundations of Software Engineering and Computer Aided Verification.

Nguyen, who serves as an organizer and program chair of VNN-COMP 2025, emphasized the significance of the competition in shaping the research landscape.

"The field of neural network verification is rapidly maturing, and VNN-COMP has become the standard for evaluating progress," he said. "Many research papers now compare their tools against VNN-COMP results or use its benchmarks for evaluation. It's exciting to be involved in shaping the competition while also contributing a tool that pushes the research frontier."

David Rosenblum, chair of the Department of Computer Science, was thrilled with ROARS Lab’s achievement. "ThanhVu Nguyen is an established research leader on problems at the intersection of formal methods and deep learning. This team’s outstanding achievement has demonstrated the great potential impact of verification technologies for AI safety," he said.

The long-term goal of NeuralSAT, supported in part by Nguyen’s NSF CAREER Award and Amazon Research Award, is to remain at the forefront of AI verification research while evolving into a practical, scalable, and potentially commercial-grade solution for industry use.

George �鶹��Ƶ is advancing a bold vision for the future of safe and robust AI and is further expanding its leadership with the launch of Virginia's first master’s program in artificial intelligence in fall 2025. This program reflects the university’s deep commitment to cutting-edge education and the development of trustworthy, high-impact AI technologies.

Topics

Artificial Intelligence

National Science Foundation

Computer science; computing; Amazon

computer science

Research

Metron establishes scholarship fund in memory of George �鶹��Ƶ alum

Nathan Kahl — Wed, 14 May 2025 18:27:41 +0000

Metron establishes scholarship fund in memory of George �鶹��Ƶ alum Nathan Kahl Wed, 05/14/2025 - 14:27

In This Story

Ziyu Yao

Lishan Yang

�鶹��Ƶ's College of Engineering and Computing (CEC) distributed its first award of $2,500 from the Jimmy Chiou Jr. Memorial Endowed Scholarship to Randy Escalera, a freshman computer science student. This named endowed scholarship was created by CEC partner organization Metron, Incorporated, with a $50,000 gift in honor of Chiou, a Metron employee and George �鶹��Ƶ alum who passed away suddenly in 2023.

Metron’s gift amount guarantees the scholarship will last in perpetuity and be granted annually. To receive the scholarship, a student must be an undergraduate majoring in computer science and be full-time and Virginia resident. Recipients will qualify on the basis of academic merit and be selected by a committee appointed by the CEC dean in coordination with the Office of Student Financial Aid.

A statement from Metron said, “Metron established the scholarship to honor Jimmy’s legacy by investing in George �鶹��Ƶ’s next generation of scholars. Inspired by his work ethic, intellectual curiosity, and unwavering positivity, the scholarship supports students who demonstrate a strong commitment and passion for all areas of computer science. The endowment reflects a forward-looking partnership between Metron and George �鶹��Ƶ, grounded in shared dedication to innovation, academic excellence, and interdisciplinary collaboration. Together, we aim to broaden access to exceptional talent who will push the boundaries of what’s possible in computer science.”

A number of Chiou’s instructors recalled his positive influence. Ziyu Yao, a professor of Chiou’s, said, “Jimmy was such a talented student with intellectual curiosity and perseverance. His talent, curiosity to learn, courage to challenge himself, and persistence in delivering outstanding academic progress, will be remembered.”

Assistant Professor Lishan Yang added, “Jimmy did well in class and made good friends with his classmates. He was quiet and warm-hearted.”

Chiou’s parents said they were happy to help their son’s memory live on by being able to help future students. His father said, “Jimmy just liked to help people. He was a very simple person.”

Topics

Scholarships

Scholarship Recipient

computer science

Alumni

endowed scholarship

George �鶹��Ƶ’s Imaging and Vision Lab illuminates the future of digital production

Teresa Donnellan — Mon, 05 May 2025 19:57:46 +0000

George �鶹��Ƶ’s Imaging and Vision Lab illuminates the future of digital production Teresa Donnellan Mon, 05/05/2025 - 15:57

In This Story

Jinwei Ye

At the intersection of imaging, computer graphics, and computer vision, �鶹��Ƶ’s Imaging and Vision Lab is pushing the boundaries of visual technology. Directed by Jinwei Ye, an associate professor in the Department of Computer Science, the lab explores every stage of the imaging pipeline—from data acquisition to 3D rendering—by designing novel algorithms, imaging systems, and immersive environments.

The lab, which is in Van Metre Hall at �鶹��Ƶ Square, has two new standout technologies in its arsenal: the Light Stage and the Pixel Cube.

The Light Stage—a spherical structure with around 150 LED lights pointing inward along with cameras—uses polarized, Wi-Fi-controlled lighting to create complex illumination patterns. This enables the lab to capture highly detailed 3D models of real-world objects, a capability that’s particularly useful in film, gaming, and robotics.

A student experimenting with Light Stage. Photo by Ron Aira/Office of University Branding

“We put objects in the center and take pictures under different lighting to recover really high-quality 3D models of real physical objects,” said Yufan Zhang, a PhD student working on this project. The Light Stage was fully designed and built by Ye’s students, providing them with a unique, hands-on engineering experience.

The Pixel Cube takes immersion a step further. Comprising 90 LED panels arranged in a cube, the system allows for panoramic simulations—perfect for applications in virtual production such as driving simulators.

“A very intuitive application of it is immersive viewing like a VR experience without using the headset,” said Ye.

But the lab’s ambitions stretch beyond visual hardware. Ye’s team is building a large dataset of everyday objects, intended to support generative AI development for uses ranging from entertainment to robotic training.

A student in the Pixel Cube. Photo by Ron Aira/Office of University Branding

“We’re creating a large 3D model dataset of diverse real-world objects, which can be used as assets either in films or in games or shown to robots,” Ye said.

Collaboration is key to the lab’s impact, added Ye. Her team, focused on advancing computational photography and AI-integrated imaging workflows, remains committed to developing foundational tools for tomorrow’s imaging technologies. They work closely with other George �鶹��Ƶ faculty and industry partners and invite potential collaborators to reach out about interdisciplinary projects in fields such as film studies, video game development, creative visual arts, simulation, and virtual training.

“We really want to make full use of this [equipment], so we want as many people as possible to use it,” said Ye.

With its combination of advanced equipment, collaborative ethos, and dedication to hands-on student involvement, the Imaging and Vision Lab is making George �鶹��Ƶ a destination for next-generation research in computer vision and graphics.

Topics

computer science

Anonymity’s ARX nemesis

In This Story

Related Stories

Topics

Bluetooth blues? George �鶹��Ƶ turns a bug into a big win

In This Story

Related News

Topics

AI’s blind spots, one PhD student’s clear vision

Related News

Topics

One tiny flip that opens a backdoor in AI

Related Stories

Topics

Barbara Snyder honored by National Academic Advising Association for excellence as an advising administrator

How long have you worked at George �鶹��Ƶ? How has your job changed over the years?

What are your main responsibilities in your role?

What do you like best about your job?

You were recognized at the recent NACADA regional conference with their Excellence in Advising—Advising Administrator award. What are your biggest takeaways from their conferences?

Do any memorable moments stand out in your academic advising experience?

Read more like this

Topics

College of Engineering and Computing mourns the passing of Mark Pullen

In This Story

Topics

Advisors from George �鶹��Ƶ receive National Academic Advising Association honors

What are your main responsibilities in your role? What types of students do you advise?

What do you like best about your job?

What are some of the biggest challenges in your role?

Have you previously attended the NACADA conference? What do you enjoy most about the conference and the organization?

What memorable moments stand out to you in your academic advising experiences?

Read More Like This

Topics

George �鶹��Ƶ’s ROARS lab retains its ranking as a leader in AI safety at the 2024 International Neural Network Verification Competition

In This Story

Topics

Metron establishes scholarship fund in memory of George �鶹��Ƶ alum

In This Story

Topics

George �鶹��Ƶ’s Imaging and Vision Lab illuminates the future of digital production

In This Story

Topics