Seminar Series: Security
UMass AI&Sec SP'25 Seminar: Sahar Abdelnabi, Evaluating and Securing LLM-Agentic Networks
Abdelnabi will discuss his work on evaluating multi-agent negotiations and how that can be beneficial to test reasoning and create evolving, dynamic benchmarks.
UMass AI&Sec SP'25 Seminar: Andy Zou, Red Teaming AI Agents In-The-Wild: Revealing Deployment Vulnerabilities
This presentation demonstrates how red teaming uncovers critical vulnerabilities in AI agents that challenge assumptions about safe deployment.
UMass AI&Sec SP'25 Seminar: Ilia Shumailov (Google Deepmind), Beyond model.generate(): Can I Even Tell What Is Going On and Why It Matters
Ilia Shumailov is a research scientist formerly at Google DeepMind, where he focused on machine learning security and adversarial vulnerabilities.
CSSI and Institute of Diversity Sciences Seminar
Please save the date for this CSSI event—updated event info will be posted on http://www.cssi.umass.edu/events.
UMass AI&Sec Fall'25 Seminar: Arman Zharmagambetov, Security and Privacy Evaluation of Autonomous AI Agents
Arman Zharmagambetov is a research scientist in the Fundamental AI Research (FAIR) team at Meta. His research primarily focuses on machine learning and...
UMass AI&Sec SP'25 Seminar: Javier Rando, Gradient-based Jailbreak Images for Multimodal Fusion Models
In this talk, Rando will introduce the notion of a tokenizer shortcut that approximates tokenization with a continuous function and enables continuous...
UMass AI&Sec SP'25 Seminar: Ryan McKenna (Google), Private Analytics and Learning at Google
In this talk, McKenna will give a broad overview of how they think about the many dimensions of data privacy at Google.
UMass AI&Sec Fall'25 Seminar: Benjamin Laufer, AI Ecosystems: Structure, Strategy, Risk and Regulation
The development of artificial intelligence is increasingly shaped by interactions between general-purpose model creators, downstream fine-tuners, regulators...
Seminar: Adam Bates (University of Illinois Urbana-Champaign), Don’t shout “Bingo!” Understanding (and Addressing) the Shortcomings of Enterprise Threat Detection Products
We are still awful at preventing data breaches and other cybersecurity incidents. In this talk, Adam Bates will describe our efforts to better understand...
UMass AI&Sec Fall'25 Seminar: Madiha Zahrah Choksi, Terms of Care: Designing Participatory Data Governance for Disability Communities
Madiha Zahrah Choksi is a PhD candidate in Computing and Information Science at Cornell Tech.
UMass AI&Sec SP'25 Seminar: Anshuman Suri, White-box v/s Black-box: Privacy Auditing for Machine Learning
In this talk, Anshuman Suri will challenge these assumptions and demonstrate that optimal membership inference does require parameter access.
UMass AI&Sec SP'25 Seminar: Norman Mu (xAI), A Closer Look at System Prompt Robustness
Norman Mu is a Member of Technical Staff at xAI, focusing on AI safety. He earned his Ph.D. in Computer Science from the University of California, Berkeley...