SpecGuard: Inference-Time Backdoor Detection For Free
SpecGuard detects backdoored LLM behavior at inference time using speculative decoding acceptance rates, adding no extra model computation.
1 stories, newest first · one card per story
SpecGuard detects backdoored LLM behavior at inference time using speculative decoding acceptance rates, adding no extra model computation.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views