QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3329-3338
Abstract
We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting, where the adversary only has query access to the top-k ranked unlabeled images from the database. Compared with query attacks in image classification, which produce adversaries according to the returned labels or confidence score, the challenge becomes even more prominent due to the difficulty in quantifying the attack effectiveness on the partial retrieved list. In this paper, we make the first attempt in Query-based Attack against Image Retrieval (QAIR), to completely subvert the top-k retrieval results. Specifically, a new relevance-based loss is designed to quantify the attack effects by measuring the set similarity on the top-k retrieval results before and after attacks and guide the gradient optimization. To further boost the attack efficiency, a recursive model stealing method is proposed to acquire transferable priors on the target model and generate the prior-guided gradients. Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting. The attack evaluations on the real-world visual search engine show that it successfully deceives a commercial system such as Bing Visual Search with 98% attack success rate by only 33 queries on average.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- ZOO2017
- IR evaluation methods for retrieving highly relevant documentsACM SIGIR Forum, 2017
- Practical Black-Box Attacks against Machine Learning2017
- Deep Residual Learning for Image Recognition2016
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations2016
- Random Gradient-Free Minimization of Convex FunctionsFoundations of Computational Mathematics, 2015
- FaceNet: A unified embedding for face recognition and clustering2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Dimensionality Reduction by Learning an Invariant Mapping2006
- On Estimation of a Probability Density Function and ModeThe Annals of Mathematical Statistics, 1962