arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.08094cs.CV

DarkHash：针对深度哈希的无数据后门攻击

DarkHash: A Data-Free Backdoor Attack Against Deep Hashing

School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络安全工程学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）

Ziqi Zhou, Menghao Deng, Yufei Song, Hangtao Zhang, Wei Wan, Shengshan Hu, Minghui Li, Leo Yu Zhang, Dezhong Yao

备注：
Accepted by TIFS 2025
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出首个无数据后门攻击DarkHash，通过双语义引导和拓扑对齐损失，在无训练数据下植入后门并保持检索精度，实验验证其高效性和抗防御能力。

摘要：

得益于其优越的特征学习能力和效率，深度哈希在大规模图像检索中取得了显著成功。近期研究表明，深度哈希模型易受后门攻击。尽管这些研究展示了有前景的攻击结果，但它们依赖于访问训练数据集来植入后门。在现实世界中，由于隐私保护和知识产权问题，获取此类数据（如身份信息）往往被禁止。在无法访问训练数据的情况下将后门嵌入深度哈希模型，同时保持原始任务的检索精度，是一个新颖且具有挑战性的问题。在本文中，我们提出了DarkHash，这是首个针对深度哈希的无数据后门攻击。具体而言，我们设计了一种具有双语义引导的新型影子后门攻击框架。它通过使用替代数据集仅微调受害模型的特定层，来嵌入后门功能并保持原始检索精度。我们考虑利用单个样本与其邻居之间的关系来增强训练期间的后门攻击。通过设计拓扑对齐损失，我们优化单个和邻近的毒化样本朝向目标样本，进一步增强攻击能力。在四个图像数据集、五种模型架构和两种哈希方法上的实验结果表明，DarkHash具有高效性，优于现有的最先进后门攻击方法。防御实验表明，DarkHash能够抵御现有的主流后门防御方法。

英文摘要：

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 specific layers of the victim model using a surrogate dataset. We consider leveraging the relationship between individual samples and their neighbors to enhance backdoor attacks during training. By designing a topological alignment loss, we optimize both individual and neighboring poisoned samples toward the target sample, further enhancing the attack capability. Experimental results on four image datasets, five model architectures, and two hashing methods demonstrate the high effectiveness of DarkHash, outperforming existing state-of-the-art backdoor attack methods. Defense experiments show that DarkHash can withstand existing mainstream backdoor defense methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑