Topic
Privacy Auditing
Discover key takeaways from 3 podcast episodes about this topic.
Large Language ModelsMembership Inference AttacksPrivacy Auditing
Jan 27, 2026Worst-Case Membership Inference of Language Models
This talk introduces a novel, highly effective strategy for generating 'canaries' to audit language models for membership inference, revealing a critical disconnect between audit success and actual privacy risk.
G
Google TechTalks
Large Language ModelsPrivacy AuditingData Memorization
Jan 27, 2026Privacy Auditing of Large Language Models
Existing methods for privacy auditing in Large Language Models (LLMs) systematically underestimate worst-case data memorization, necessitating new canary strategies for effective empirical leakage detection.
G
Google TechTalks
Differential PrivacyPrivacy AuditingMachine Learning
Jan 27, 2026The Limits and Possibilities of One Run Auditing
This talk dissects the theoretical limitations of one-run privacy auditing for differential privacy while demonstrating its practical effectiveness and outlining pathways for significant improvement.
G
Google TechTalks