Spring 2025 seminar COMPSCI 692PA on AI Security and Privacy
2/3/25 |
Anshuman Suri (Northeastern University): White-box vs Black-box: Privacy Auditing for Machine Learning (abstract) |
2/10/25 |
Sahar Abdelnabi (Microsoft): Evaluating and Securing LLM-Agentic Networks (abstract) |
2/20/25 |
Javier Rando (ETH Zurich): Gradient-based Jailbreak Images for Multimodal Fusion Models (abstract) |
2/24/25 |
|
3/3/25 |
Harsh Chaudhari (Northeastern University): Propagation of Adversarial Bias to Distilled Language Models (abstract) |
3/10/25 |
Andy Zou (Carnegie Mellon Univerosity): Red Teaming AI Agents in-the-wild: Revealing Deployment Vulnerabilities (abstract) |
3/24/25 |
Xiangyu Qi (OpenAI): Safety Alignment Should Be Made More Than Just A Few Tokens Deep (abstract) |
3/31/25 |
Om Thakkar (OpenAI): Privacy Leakage in Speech Models: Attacks and Mitigations (abstract) |
4/7/25 |
Ryan McKenna (Google): Private Analytics and Learning at Google (abstract) |
4/10/25 |
Milad Nasr (Google): Topic TBD |
4/18/25 |
Edoardo Debenedetti (ETH Zurich): Defeating Prompt Injections by Design |
4/28/25 |
Jonas Geiping (ELLIS Institute): Topic TBD |
5/5/25 |
Speaker TBD (TBD): Topic TBD |