Eugene Bagdasarian

Eugene Bagdasarian

Assistant Professor, UMass Amherst CICS, he/him

eugene@umass.edu
Office: CS 304

About

I am an Assistant Professor at UMass Amherst CICS. In our group, we look at security and privacy attack vectors for AI systems deployed in real-life. I am part-time at Google working on privacy-conscious agents.

I completed my PhD at Cornell Tech advised by Vitaly Shmatikov and Deborah Estrin. My research was recognized by Apple Scholars in AI/ML and Digital Life Initiative fellowships, and Usenix Security Distinguished Paper Award. At UMass, we got Schmidt Sciences AI Safety Grant. I received an engineering degree from Baumanka and worked at Cisco as a software engineer before going to grad school.

I grew up in Tashkent and play water polo.

Announcement 1: I am looking for PhD students (apply) and post-docs to work on attacks on LLM agents and generative models. Please reach out over email and fill the form!

Announcement 2: We are running a seminar on Privacy and Security for GenAI, please sign up if you are interested.

Research

Security: We worked on backdoor attacks in federated learning and proposed frameworks Backdoors101 and Mithridates, and an attack on generative language models covered by VentureBeat and The Economist. We studied vulnerabilities in multi-modal and agentic systems: self-interpreting images, adversarial illusions and backdooring bias into diffusion models. We recently did an OverThink attack on reasoning models.

Privacy: We proposed AirGapAgent for privacy protection in agentic applications leveraging Contextual Integrity. Before, I also worked on aspects of differential privacy including fairness trade-offs, applications to location heatmaps, and tokenization methods for private federated learning. Additionally, we built the Ancile system that enforces use-based privacy of user data.

PhD student(s): Abhinav Kumar. Recent collaborators: Amir Houmansadr, Shlomo Zilberstein, Brian Levine, Kyle Wray, Ali Naseh, Jaechul Roh, Dzung Pham, June Jeong, and many others.

Current Funding:

Teaching

Courses

CS 360: Intro to Security, SP 25.

CS 692PA: Seminar on Privacy and Security for GenAI models, FA'24, SP'25, FA'25

CS 690: Trustworthy and Responsible AI, FA'25 (link TBD)

Service

Academic Service

Program Committees:

  • ACM CCS'24/'25, ICLR'25, IEEE S&P'25

Workshop Organizer:

Broadening Participation

Eugene co-organizes PLAIR (Pioneer Leaders in AI and Robotics), an outreach program that introduces high school students across Western Massachusetts to the world of robotics and AI safety. Please reach out if you are interested in joining.

Recent News