Unsupervised Adversarial Attacks On Deep Feature-based Retrieval With GAN

Abstract

Studies show that Deep Neural Network (DNN)-based image classification models are vulnerable to maliciously constructed adversarial examples. However, little effort has been made to investigate how DNN-based image retrieval models are affected by such attacks. In this paper, we introduce Unsupervised Adversarial Attacks with Generative Adversarial Networks (UAA-GAN) to attack deep feature-based image retrieval systems. UAA-GAN is an unsupervised learning model that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query images to form adversarial queries. The core idea is to ensure that the attached perturbation is barely perceptible to human yet effective in pushing the query away from its original position in the deep feature space. UAA-GAN works with various application scenarios that are based on deep features, including image retrieval, person Re-ID and face search. Empirical results show that UAA-GAN cripples r

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhao2019unsupervised

Related papers

• Prototype-supervised Adversarial Network For Targeted Attack Of Deep Hashing (2021)15.97
• Binary Generative Adversarial Networks For Image Retrieval (2017)18.34
• Targeted Mismatch Adversarial Attack: Query With A Flower To Retrieve The Tower (2019)13.23
• Unsupervised Multi-criteria Adversarial Detection In Deep Image Retrieval (2023)0.00
• Generative Adversarial Nets For Information Retrieval: Fundamentals And Advances (2018)0.00
• Deep Semantic Hashing With Generative Adversarial Networks (2018)13.50
• Adversarial Attack On Deep Product Quantization Network For Image Retrieval (2020)11.29
• Adversarial Training For Sketch Retrieval (2016)11.19