Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 22 Mar 2023.
Builds on
31 of 53 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2015Fast R-CNNcited by 2,930
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
19 more
- 2016Adversarial Machine Learning at Scalecited by 934
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
- 2017Evasion Attacks against Machine Learning at Test Timecited by 686
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
- 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
- 2020Bag of Tricks for Adversarial Trainingcited by 199
- 2017HashNet: Deep Learning to Hash by Continuationcited by 121
- 2016A Survey on Learning to Hashcited by 119
- 2019Central Similarity Quantization for Efficient Image and Video Retrievalcited by 77
- 2022Improving Vision Transformers by Revisiting High-frequency Componentscited by 75
- 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
- 2015Simultaneous Feature Learning and Hash Coding with Deep Neural Networkscited by 44
- 2017Deep Supervised Discrete Hashingcited by 36
- 2017Asymmetric Deep Supervised Hashingcited by 35
- 2020Targeted Attack for Deep Hashing based Retrievalcited by 34
- 2022One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matchingcited by 9
- 2021Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashingcited by 8
- 2022CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrievalcited by 2
Built on by
Not cited yet.