ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
[Widzenie komputerowe] Autorzy: Li Zeng, Mingcheng Duan, Longfei Fan i 5 więcej
With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulnerabilities like backdoor attacks that severely compromise model integrity. Specifically, such attacks involve altering the categories of objects (i.e., object misclassification), removing bounding boxes (i.e., object disappearance), or generating bounding box proposals for non-existent objects (i.e., object generation) when a predefined trigger is present in the input. Although backdoor defenses for image classification are well-established, the research for object detection remains comparatively underexplored. Existing defenses address these threats by scanning outputs or models for potential backdoors but require discarding either malicious data or models. This remedy fails to enable a continuous and accurate perceptual stream for the o…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe