作者位次 #6/9ACL 2026Poster· Natural Language Processing
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption
Yuanhong Huang · Huili Wang · Xueying Bai · Jinrui Wang · Jiajun Liu · Ziqin Wang · Wanchun Ni · Shangguang Wang · Tao Qi
摘要
Membership inference attack (MIA) has emerged as a promising tool for auditing the training data of LLMs, supporting data privacy and copyright protection. Most existing MIA methods rely on the assumption that LLMs assign higher confidence scores to training samples than to non-training ones.Howe...