DMV Security Workshop 2025
Explore the forefront of security research at our exclusive workshop, uniting aspiring researchers from Washington D.C., Maryland, and Virginia.
Workshop at a Glance
The DMV Security Workshop is launching its second event in the 2024-2025 academic year! This series aims to unite researchers in computer security and privacy from Washington, D.C.
, Maryland
, and Virginia
.
This workshop will be an in-person event
at the Virginia Tech Research Center - Arlington, 900 N. Glebe Road, Second Floor, Arlington, VA 22203, on March 28th, 2025
. The program will include speed advising, lightning talks by faculty and students, and breakout discussion sessions. Unlike traditional conferences, the DMV Security Workshop emphasizes future collaborations over past work presentations, offering a unique platform for seeding new partnerships and ideas.
The event is open to all researchers in the field from the DMV area. To encourage broad participation, registration is free. Coffee and light snacks will be provided during breaks; however, participants are on their own for covering the costs of meals, transportation, accommodations, and other logistics.
Venue
Virginia Tech Research Center - Second Floor
900 N. Glebe Road, Arlington, VA 22203
Registration
Schedule
Time (EST) | |
---|---|
9:30 | Registration and Coffee |
9:50 | Welcome and Overview |
10:00 | Keynote Talk: Watermarks in the Sand: The Illusion of Reliable Attribution in Generative AI Prof. Giuseppe Ateniese (George Mason University) ![]() Abstract Generative AI produces remarkably realistic outputs, complicating efforts to distinguish human creations from synthetic content. A popular response embeds subtle statistical watermarks to certify authenticity. This talk systematically evaluates the fundamental reliability of watermarking, revealing that seemingly robust watermarks can always be removed through incremental, quality-preserving perturbations. Through systematic analysis and clear empirical demonstrations, it becomes evident that robust watermarking—resilient to removal without degrading output quality—is fundamentally unachievable. The results highlight that watermarking is no dependable safeguard, guiding us toward more cautious and realistic approaches to digital provenance. This is based on a paper that was presented at ICML 2024. Biography Giuseppe Ateniese is a Professor, Eminent Scholar in Cybersecurity and CCI Faculty Fellow in the Department of Computer Science and the Department of Cyber Security Engineering at George Mason University. He was Farber Endowed Chair in Computer Science and Department Chair at Stevens Institute of Technology. In addition, he was with Sapienza-University of Rome (Italy), Assistant/Associate Professor at Johns Hopkins University (USA), and one of the JHU Information Security Institute founders. He was a researcher at IBM Zurich Research lab (Switzerland) and scientist at the Information Sciences Institute of the University of Southern California (USA). He also briefly worked as visiting professor at Microsoft in Redmond (USA). He received the NSF CAREER Award for his research in privacy and security, and the Google Faculty Research Award, the IBM Faculty Award, and the IEEE CISTC Technical Recognition Award for his research on cloud security. He has contributed to areas such as proxy re-cryptography, anonymous communication, two-party computation, secure storage, and provable data possession. He is currently working on privacy-preserving machine learning and decentralized secure computing based on the blockchain technology. |
11:00 | Lightning Talks 10-12 minutes talks about research. • Yixin Sun, Assistant Professor (UVA ): Data-driven Network Security and Privacy • Changqing Luo, Assistant Professor (VCU ): Fingerprinting AI Models • Thang Hoang, Assistant Professor (VT ): Towards Practical Privacy-Enhancing Technologies • Marco Paes, Research Scientist (CMU ): TRACE: Threat Recognition through Administrative Correlation and Extraction • Arkady Yerukhimovich, Assistant Professor (GWU ): Cryptography for an Untrustworthy World |
12:00 | Lunch and Student Poster Session |
1:30 | Speed Advising Speed advising sessions enable students to meet for 15 minutes each with faculty from other universities. Mentors will stay in place, and students will come to them. Faculty Advisors: Tianhao Wang (UVA), Yixin Sun (UVA), Jie Zhou (GWU), Zhuangdi Zhu (GMU), Xiaokuan Zhang (GMU), Thang Hoang (VT), Jane (Yanjun Qi) (UVA), Adwait Jog (UVA), Evgenios Kornaropoulos (GMU) |
2:45 | Break |
3:00 | Lightning Talks 10-12 minutes talks about research. • Adwait Jog, Associate Professor (UVA ): Confidential Computing with GPUs: Challenges and Opportunities • Mingrui Liu, Assistant Professor (GMU ): Hierarchical Optimization: Algorithmic Foundation and Applications in (Trustworthy) Machine Learning • Tianhao Wang, Assistant Professor (UVA ): Differentially Private Data Synthesis |
3:45 | NSF Office Hour Dr. Karen Karavanic (Program Director, SaTC 2.0) |
4:45 | Concluding Remarks |