Paper proposes ASR_STEP to discount iterative LLM jailbreaks
On JailBreakBench, discounting victim-model calls lowers GCG by 7.0 to 8.7 points and PAIR by 3.4 to 12.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #gcg
HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving
HoneyRoute detects malicious LLM serving requests and diverts them to a honeypot model, reaching F1 0.911 with 38 ms median added latency.