Adversarial Sticker: A Stealthy Attack Method in the Physical World
Authors:
Top Cited Papers
- 23 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1
Abstract
To assess the vulnerability of deep learning in physical world, recent works introduce adversarial patch and apply it on different tasks. In this paper, we propose another kind of adversarial patch: Meaningful Adversarial Sticker, a physically feasible and stealthy attack method by using real stickers existing in our life. Instead of previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position, 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 physical world. Besides, to make adversarial stickers more practical in real scenes, we conduct attacks in the black-box setting with limited information rather than the white-box setting with all the details of threat models. To effectively solve the sticker's parameters, we design Region based Heuristic Differential Algorithm, which utilizes the new-found regional aggregation of effective solutions and the adaptive adjustment strategy of evaluation criteria. Our method is comprehensively verified in Face Recognition and then extended to Image Retrieval and Traffic Sign Recognition. Extensive experiments show the proposed method is effective and efficient in complex physical conditions and has good generalization for different tasksKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (No.62076018, 61806109)
This publication has 37 references indexed in Scilit:
- ZOO2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Accessorize to a Crime2016
- UnitBox2016
- Traffic-Sign Detection and Classification in the Wild2016
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- FaceNet: A unified embedding for face recognition and clustering2015
- A morphable model for the synthesis of 3D faces1999