Google TechTalks
Worst-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.
Privacy 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.
Threat Models for Memorization: Privacy, Copyright, and Everything In-Between
Relaxing threat models for machine learning memorization, even with natural data or benign users, creates unexpected privacy and copyright vulnerabilities in AI models.
Want more on large language models?
Explore deep-dive summaries and actionable takeaways from the best minds across different podcasts discussing this topic.
View All Large Language Models Episodes→Don't see the episode you're looking for?
We're constantly adding new episodes, but if you want to see a specific one from Google TechTalks summarized, let us know!
Submit an Episode