Topic
Copyright Infringement
Discover key takeaways from 2 podcast episodes about this topic.
Membership Inference Attacks (MIA)Large Language Models (LLMs)N-gram Coverage
Jan 27, 2026The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
Discover how a simple n-gram coverage attack can surprisingly and effectively detect if specific data was used to train large language models, even with limited black-box access.
G
Google TechTalks
Large Language Models (LLMs)Data MemorizationCopyright Infringement
Jan 27, 2026Evaluating Data Misuse in LLMs: Introducing Adversarial Compression Rate as a Metric of Memorization
This presentation introduces Adversarial Compression Rate (ACR) as a robust metric to quantify LLM memorization, addressing copyright concerns by focusing on the shortest prompt needed to elicit exact verbatim output.
G
Google TechTalks