AIBearisharXiv – CS AI · 14h ago7/10
🧠
Powerful Training-Free Membership Inference Against Autoregressive Language Models
Researchers have developed EZ-MIA, a training-free membership inference attack that dramatically improves detection of memorized data in fine-tuned language models by analyzing probability shifts at error positions. The method achieves 3.8x higher detection rates than previous approaches on GPT-2 and demonstrates that privacy risks in fine-tuned models are substantially greater than previously understood.
🧠 Llama