Leaky Thoughts
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
This work explores how reasoning traces in large reasoning models (LRMs) leak private user data, despite being assumed internal and safe. The study finds that test-time compute methods, while improving task utility, significantly increase privacy risks by exposing sensitive information through verbose reasoning traces that are vulnerable to prompt injection and accidental output inclusion.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack