Semantic-aware Adversarial Training For Reliable Deep Hashing Retrieval

Abstract

Deep hashing has been intensively studied and successfully applied in large-scale image retrieval systems due to its efficiency and effectiveness. Recent studies have recognized that the existence of adversarial examples poses a security threat to deep hashing models, that is, adversarial vulnerability. Notably, it is challenging to efficiently distill reliable semantic representatives for deep hashing to guide adversarial learning, and thereby it hinders the enhancement of adversarial robustness of deep hashing-based retrieval models. Moreover, current researches on adversarial training for deep hashing are hard to be formalized into a unified minimax structure. In this paper, we explore Semantic-Aware Adversarial Training (SAAT) for improving the adversarial robustness of deep hashing models. Specifically, we conceive a discriminative mainstay features learning (DMFL) scheme to construct semantic representatives for guiding adversarial learning in deep hashing. Particularly, our DMFL

Stats

• citations33
• S2 citations—
• github stars9
• HF likes0
• heat score13.49
• arxiv keyyuan2023semantic

Related papers

• Cgat: Center-guided Adversarial Training For Deep Hashing-based Retrieval (2022)8.42
• Unsupervised Multi-criteria Adversarial Detection In Deep Image Retrieval (2023)0.00
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Reliable And Efficient Evaluation Of Adversarial Robustness For Deep Hashing-based Retrieval (2023)0.00
• Self-supervised Asymmetric Deep Hashing With Margin-scalable Constraint (2020)0.00
• Darkhash: A Data-free Backdoor Attack Against Deep Hashing (2025)2.26
• Targeted Attack For Deep Hashing Based Retrieval (2020)13.65
• Diffhash: Text-guided Targeted Attack Via Diffusion Models Against Deep Hashing Image Retrieval (2025)0.00