Unrestricted Targeted Deep Hashing Attack via Contrastive Latent Diffusion
UTDHA is proposed, the first unrestricted targeted attack for deep hashing models using contrastive-guided latent diffusion and outperforms existing targeted adversarial attack baselines for deep hashing models in both attack effectiveness and imperceptibility.
Fan Yang, Chuanchuan Ma, Yuhui Zheng et al.
· 0 citations