Seminar Series: Security

Abdelnabi will discuss his work on evaluating multi-agent negotiations and how that can be beneficial to test reasoning and create evolving, dynamic benchmarks.

This presentation demonstrates how red teaming uncovers critical vulnerabilities in AI agents that challenge assumptions about safe deployment.

Ilia Shumailov is a research scientist formerly at Google DeepMind, where he focused on machine learning security and adversarial vulnerabilities.

Please save the date for this CSSI event—updated event info will be posted on http://www.cssi.umass.edu/events.

How can researchers use sensitive datasets for machine learning and statistics without compromising the privacy of the individuals who contribute their data?

In this talk, Rando will introduce the notion of a tokenizer shortcut that approximates tokenization with a continuous function and enables continuous...

In this talk, McKenna will give a broad overview of how they think about the many dimensions of data privacy at Google.

The development of artificial intelligence is increasingly shaped by interactions between general-purpose model creators, downstream fine-tuners, regulators...

We are still awful at preventing data breaches and other cybersecurity  incidents. In this talk, Adam Bates will describe our efforts to better understand...

In this talk, Anshuman Suri will challenge these assumptions and demonstrate that optimal membership inference does require parameter access.

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...

Jonas Geiping is a Research Group Leader at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems.