Ilia Shumailov

3

Papers

30

Total Citations

1

Affiliations

Affiliations

Google Deepmind

Papers (3)

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

Measuring memorization in RLHF for code completion

Exploring the limits of strong membership inference attacks on large language models

NeurIPS 2025arXiv