Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present. Existing detection methods either rely on trigger inversion or exploit architecture-specific assumptions, and critically, representative existing methods fail to generalize reliably to scene-level attacks, where a single trigger…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
