Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness. Recently, several adversarial attacks have been presented to reveal the vulnerability of deep hashing models against adversarial examples. However, existing attack methods suffer from degraded performance or inefficiency because they underutilize the semantic relations between original samples or spend a lot of time learning these relations with a deep neural network. In this paper, we propose a novel Pharos-guided Attack, dubbed PgA, to evaluate the adversarial robustness of deep hashing networks reliably and efficiently. Specifically, we design pharos code to represent the semantics of the benign image, which preserves the similarity to semantically relevant samples and dissimilarity to irrelevant ones. It is proven that we can quickly calculate the pharos code via a simple math formula. Accordingly, PgA can directly conduct a reliable and efficient attack on deep hashing-based retrieval by maximizing the similarity between the hash code of the adversarial example and the pharos code. Extensive experiments on the benchmark datasets verify that the proposed algorithm outperforms the prior state-of-the-arts in both attack strength and speed.

翻译：深度哈希因其高效性和有效性被广泛应用于大规模图像检索。近年来，多种对抗攻击方法被提出以揭示深度哈希模型在对抗样本面前的脆弱性。然而，现有攻击方法因未能充分利用原始样本间的语义关联，或需耗费大量时间通过深度神经网络学习这些关联，导致性能下降或效率低下。本文提出一种名为Pharos引导攻击（PgA）的新型方法，旨在可靠且高效地评估深度哈希网络的对抗鲁棒性。具体而言，我们设计了"灯塔码"（pharos code）来表征良性图像的语义信息，该码能够保持与语义相关样本的相似性以及与无关样本的相异性。理论证明，通过简单的数学公式即可快速计算灯塔码。基于此，PgA通过最大化对抗样本哈希码与灯塔码之间的相似性，直接对基于深度哈希的检索系统实施可靠且高效的攻击。在基准数据集上的大量实验验证表明，本算法在攻击强度与速度两方面均优于现有最优方法。