Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval
This work addresses the vulnerability of deep hashing models to adversarial attacks, which is crucial for ensuring reliable image retrieval systems, though it is incremental as it improves upon existing attack methods.
The paper tackles the problem of evaluating adversarial robustness in deep hashing-based image retrieval by proposing a novel Pharos-guided Attack (PgA), which outperforms prior methods in both attack strength and speed, as verified by extensive experiments on benchmark datasets.
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.