Ruixuan Liu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
The paper introduces $(l, b)$-inextractability, a new formal measure that demonstrates that standard indistinguishability properties are insufficient for guaranteeing protection against data extraction from LLM APIs.
Highlighted terms show continued research focus across papers