Papers
arxiv:1809.02681

Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval

Published on Oct 20, 2020
Authors:
,
,
,

Abstract

An adversarial attack method is developed to specifically target image retrieval systems by generating adversarial queries that exploit feature-level gradients and demonstrate superior attack performance compared to traditional classification-based approaches.

Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges in applying prevailing image recognition attack methods to image retrieval. First, image retrieval demands discriminative visual features, which is significantly different from the one-hot class prediction in image recognition. Second, due to the disjoint and potentially unrelated classes between the training and test set in image retrieval, predicting the query category from predefined training classes is not accurate and leads to a sub-optimal adversarial gradient. To address these limitations, we propose a new white-box attack approach, Opposite-Direction Feature Attack (ODFA), to generate adversarial queries. Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space. To our knowledge, we are among the early attempts to design an attack method specifically for image retrieval. When we deploy an attacked image as the query, the true matches are prone to receive low ranks. We demonstrate through extensive experiments that (1) only crafting adversarial queries is sufficient to fool the state-of-the-art retrieval systems; (2) the proposed attack method, ODFA, leads to a higher attack success rate than classification attack methods, validating the necessity of leveraging characteristics of image retrieval; (3) the adversarial queries generated by our method have good transferability to other retrieval models without accessing their parameters, i.e.,the black-box setting.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1809.02681 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1809.02681 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1809.02681 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.