membership inference attacks

7 papers

• Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
• Exploring the limits of strong membership inference attacks on large language models
• Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
• LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
• Permissioned LLMs: Enforcing Access Control in Large Language Models
• Practical Bayes-Optimal Membership Inference Attacks
• Vid-SME: Membership Inference Attacks against Large Video Understanding Models