Attack is the Best Defense: Towards Preemptive-Protection Person Re-Identification

Lin Wang, Wanqian Zhang, Dayan Wu, Fei Zhu, Bo Li

Abstract: Person Re-IDentification (ReID) aims at retrieving images of the same person across multiple camera views. Despite its popularity in surveillance and public safety, the leakage of identity informa- tion is still at risk. For example, once obtaining the illegal access to ReID systems, malicious user can accurately retrieve the target person, leading to the exposure of private information. Recently, some pioneering works protect private images with adversarial examples by adding imperceptible perturbations to target images. However, in this paper, we argue that directly applying adversary- based methods to protect the ReID system is sub-optimal due to the ‘overlap identity’ issue. Specifically, merely pushing the adversarial image away from its original label would probably make it move into the vicinity of other identities. This leads to the potential risk of being retrieved when querying with all the other identities ex- haustively. We thus propose a novel preemptive-Protection person Re-IDEntification (PRIDE) method. By explicitly constraining the adversarial image to an isolated location, the target person is far away from neither the original identity nor any other identities, which protects him from being retrieved by illegal queries. More- over, we further propose two crucial attack scenarios (Random Attack and Order Attack) and a novel Success Protection Rate (SPR) metric to quantify the protection ability. Experiments show con- sistent outperformance of our method over other baselines across different ReID models, datasets and attack scenarios.