Adversarial Sticker: A Stealthy Attack Method in the Physical World

TL;DR

This paper introduces a stealthy physical attack method using real stickers, manipulating their placement and orientation to deceive deep learning systems across various tasks.

Contribution

It proposes a new type of adversarial patch called Meaningful Adversarial Sticker, utilizing position and rotation for physical attacks in black-box settings.

Findings

Effective in face recognition, image retrieval, and traffic sign recognition.

Maintains attack performance despite physical distortions.

Demonstrates good generalization across different tasks.

Abstract

To assess the vulnerability of deep learning in the physical world, recent works introduce adversarial patches and apply them on different tasks. In this paper, we propose another kind of adversarial patch: the Meaningful Adversarial Sticker, a physically feasible and stealthy attack method by using real stickers existing in our life. Unlike the previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position and rotation angle on the objects to perform physical attacks. Because the position and rotation angle are less affected by the printing loss and color distortion, adversarial stickers can keep good attacking performance in the physical world. Besides, to make adversarial stickers more practical in real scenes, we conduct attacks in the black-box setting with the limited information rather than the white-box setting with all the details of threat models. To effectively solve for the sticker's parameters, we design the Region based Heuristic Differential Evolution Algorithm, which utilizes the new-found regional aggregation of effective solutions and the adaptive adjustment strategy of the evaluation criteria. Our method is comprehensively verified in the face recognition and then extended to the image retrieval and traffic sign recognition. Extensive experiments show the proposed method is effective and efficient in complex physical conditions and has a good generalization for different tasks.