Universal perturbation attack against image retrieval

Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has been paid to attacking image retrieval systems. In this paper, we make the first attempt in attacking image retrieval systems. Concretely, image retrieval attack is to make the retrieval system return irrelevant images to the query at the top ranking list. It plays an important role to corrupt the neighbourhood relationships among features in image retrieval attack. To this end, we propose a novel method to generate retrieval-against UAP to break the neighbourhood relationships of image features via degrading the corresponding ranking metric. To expand the attack method to scenarios with varying input sizes or untouchable network parameters, a multi-scale random resizing scheme and a ranking distillation strategy are proposed. We evaluate the proposed method on four widely-used image retrieval datasets, and report a significant performance drop in terms of different metrics, such as mAP and mP@10. Finally, we test our attack methods on the real-world visual search engine, i.e., Google Images, which demonstrates the practical potentials of our methods.

Li Jie, Ji Rongrong, Liu Hong, Hong Xiaopeng, Gao Yue, Tian Qi

A4 Article in conference proceedings

17th IEEE/CVF International Conference on Computer Vision, ICCV 2019

J. Li, R. Ji, H. Liu, X. Hong, Y. Gao and Q. Tian, "Universal Perturbation Attack Against Image Retrieval," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 4898-4907, doi: 10.1109/ICCV.2019.00500

https://doi.org/10.1109/ICCV.2019.00500 http://urn.fi/urn:nbn:fi-fe2020060340339