Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs

ArXi:2605.20641v1 Announce Type: cross Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first uncover its numerical side effects can be maliciously exploited to implant stealthy backdoors in LLMs. We propose a unified optimization-triggered attack framework comprising two complementary strategies.