Centralized Adversarial Learning for Robust Deep Hashing

by   Xunguang Wang, et al.

Deep hashing has been extensively utilized in massive image retrieval because of its efficiency and effectiveness. Recently, it becomes a hot issue to study adversarial examples which poses a security challenge to deep hashing models. However, there is still a critical bottleneck: how to find a superior and exact semantic representative as the guide to further enhance the adversarial attack and defense in deep hashing based retrieval. We, for the first time, attempt to design an effective adversarial learning with the min-max paradigm to improve the robustness of hashing networks by using the generated adversarial samples. Specifically, we obtain the optimal solution (called center code) through a proved Continuous Hash Center Method (CHCM), which preserves the semantic similarity with positive samples and dissimilarity with negative samples. On one hand, we propose the Deep Hashing Central Attack (DHCA) for efficient attack on hashing retrieval by maximizing the Hamming distance between the hash code of adversarial example and the center code. On the other hand, we present the Deep Hashing Central Adversarial Training (DHCAT) to optimize the hashing networks for defense, by minimizing the Hamming distance to the center code. Extensive experiments on the benchmark datasets verify that our attack method can achieve better performance than the state-of-the-arts, and our defense algorithm can effectively mitigate the effects of adversarial perturbations.


page 11

page 23


Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval

Deep hashing has been extensively applied to massive image retrieval due...

Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing

Due to its powerful capability of representation learning and high-effic...

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label

Due to its powerful feature learning capability and high efficiency, dee...

Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval

Deep supervised hashing for image retrieval has attracted researchers' a...

Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval

The vulnerability in the algorithm supply chain of deep learning has imp...

Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory

The simple approach of retrieving a closest match of a query image from ...

Security analysis of cancellable biometrics using constrained-optimized similarity-based attack

Cancellable biometrics (CB) intentionally distorts biometric template fo...

Please sign up or login with your details

Forgot password? Click here to reset