Litcius/Paper detail

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label

Shengshan Hu, Ziqi Zhou, Yechao Zhang, Leo Yu Zhang, Yifeng Zheng, Yuanyuan He, Hai Jin

2022Proceedings of the 30th ACM International Conference on Multimedia35 citationsDOI

Abstract

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they cannot meet the intrinsic demand of image retrieval backdoor.

Topics & Concepts

BackdoorComputer scienceHash functionDeep learningArtificial intelligenceAdversarial systemDeep neural networksImage (mathematics)Feature (linguistics)Machine learningPattern recognition (psychology)Computer securityLinguisticsPhilosophyAdversarial Robustness in Machine LearningDomain Adaptation and Few-Shot LearningAnomaly Detection Techniques and Applications
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label | Litcius