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.
45
SpecGuard detects backdoored LLM behavior at inference time using speculative decoding acceptance rates, adding no extra model computation.
Research shows AP2 agent-payment signatures can be manipulated into valid but wrong carts; proposed A-VIP defense binds signed intent to purchases.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views