On security threats for robust perceptual hashing

Oleksiy Koval (1) , Sviatoslav Voloshynovskiy (1) , Patrick Bas (2) , François Cayre (2)

1 CVML - Computer Vision and Multimedia Laboratory [Geneve]
2 GIPSA-C2S - GIPSA - Communication, Signal et Sécurité

Perceptual hashing has to deal with the constraints of robustness, accuracy and security. After modeling the process of hash extraction and the properties involved in this process, two different security threats are studied, namely the disclosure of the secret feature space and the tampering of the hash. Two different approaches for performing robust hashing are presented: Random-Based Hash (RBH) where the security is achieved using a random pro jection matrix and Content-Based Hash (CBH) were the security relies on the difficulty to tamper the hash. As for digital watermarking, different security setups are also devised: the Batch Hash Attack, the Group Hash Attack, the Unique Hash Attack and the Sensitivity Attack. A theoretical analysis of the information leakage in the context of Random-Based Hash is proposed. Finally, practical attacks are presented: (1) Minor Component Analysis is used to estimate the secret projection of Random-Based Hashes and (2) Salient point tampering is used to tamper the hash of Content-Based Hashes systems.

Domains: Signal and Image processing; Signal and Image Processing

Oleksiy Koval, Sviatoslav Voloshynovskiy, Patrick Bas, François Cayre. On security threats for robust perceptual hashing. Media Forensics and Security, Jan 2009, San Jose, United States. pp.id 807487, ⟨10.1117/12.807487⟩. ⟨hal-00371146⟩