content type videopublished June 28, 2022
PPML Workshop Talk: What Does it Mean for a Language Model to Preserve Privacy?
AuthorsFlorian Tramèr (Google, ETH Zurich)
Related readings and updates.
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
July 10, 2026research area Methods and Algorithms, research area Privacyconference International Conference on Availability, Reliability and Security (ARES)
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (ARES) 2026.
Autonomous negotiation agents are increasingly deployed in high-stakes settings such as insurance and procurement. While cryptographic techniques protect explicitly disclosed constraint values, they fail to address a subtler threat:…
Incentivizing Temporal-Awareness in Egocentric Video Understanding Models
July 9, 2026research area Computer Vision, research area Methods and Algorithms
Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training objectives that fail to explicitly reward temporal reasoning and instead rely on frame-level spatial shortcuts. To address this limitation, we propose…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.