Widening the Gap: Exploiting LLM Quantization via Outlier Injection 事件

Widening the Gap: Exploiting LLM Quantization via Outlier Injection arXiv:2605.15152v2 Announce Type: replace-cross Abstract: LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existing quantization-conditioned attacks have been limited to relatively simple qu