Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models

Name: Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Yu He

34th USENIX Security Symposium (USENIX Security '25) · Day 1 · LLM Privacy