Darkhash: A Data-free Backdoor Attack Against Deep Hashing

Abstract

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor attacks. Although these studies have shown promising attack results, they rely on access to the training dataset to implant the backdoor. In the real world, obtaining such data (e.g., identity information) is often prohibited due to privacy protection and intellectual property concerns. Embedding backdoors into deep hashing models without access to the training data, while maintaining retrieval accuracy for the original task, presents a novel and challenging problem. In this paper, we propose DarkHash, the first data-free backdoor attack against deep hashing. Specifically, we design a novel shadow backdoor attack framework with dual-semantic guidance. It embeds backdoor functionality and maintains original retrieval accuracy by fine-tuning only specifi

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyzhou2025darkhash

Related papers

• Badhash: Invisible Backdoor Attacks Against Deep Hashing With Clean Label (2022)11.19
• Model Inversion Attack Against Deep Hashing (2025)0.00
• Clean Image May Be Dangerous: Data Poisoning Attacks Against Deep Hashing (2025)0.00
• Diffhash: Text-guided Targeted Attack Via Diffusion Models Against Deep Hashing Image Retrieval (2025)0.00
• Targeted Attack For Deep Hashing Based Retrieval (2020)13.65
• Semantic-aware Adversarial Training For Reliable Deep Hashing Retrieval (2023)13.49
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Backdoor Attack On Hash-based Image Retrieval Via Clean-label Data Poisoning (2021)2.51