Papers with auditing privacy risks
Fast-MIA: Efficient and Scalable Membership Inference for LLMs (2026.acl-demo)
Copied to clipboard
| Challenge: | a library for evaluating membership inference attacks against large language models (LLMs) has emerged as a crucial technique for auditing privacy risks and copyright infringement in LLMs. |
| Approach: | They propose a Python library for efficiently evaluating membership inference attacks against large language models (LLMs) they use a high-throughput batch inference via vLLM and a cross-method caching architecture that computes intermediate results once and shares them across methods. |
| Outcome: | The proposed library performs a 5 speedup in inference and a cross-method caching architecture that computes intermediate results once and shares them across methods. |