Loading feed…
Schneier on Security0 Hot0 comments3 min read
Schneier on Security
Two research papers examine contextual integrity in LLMs — the ability to control what personal information is appropriately shared in different task contexts. CIMemories, a new benchmark using synthetic user profiles with 100+ attributes, finds frontier models leak sensitive information inappropriately up to 69% of the time, with GPT-5's violation rate climbing from 0.1% to 25.1% as tasks and repeated runs accumulate. Privacy-conscious prompting fails to fix this, as models tend to overgeneralize into sharing everything or nothing. A second paper proposes a reinforcement learning framework that explicitly trains models to reason about context before disclosing information, showing reduced leakage while preserving task performance, with gains transferring to the established PrivacyLens benchmark.
Source: https://www.schneier.com/blog/archives/2026/08/llms-and-contextual-integrity.html. 8 Sync News only summarizes and links out; content copyright belongs to the authors and original sources.
Recommended for you
Bình luận
Đang tải bình luận…
