Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples
ACM Transactions on Software Engineering and Methodology · 31.03.2024 · 33 (3) · 1-45
DOI: 10.1145/3631977 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 15.03.2024. Verfasst von Zhe Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 128 Literaturangaben. Gefördert von: National Natural Science Foundation of China, CAS Project for Young Scientists in Basic Research, ISCAS New Cultivation Project.
Abstract (Originalsprache)
As a new programming paradigm, deep learning (DL) has achieved impressive performance in areas such as image processing and speech recognition, and has expanded its application to solve many real-world problems. However, neural networks and DL are normally black-box systems; even worse, DL-based software are vulnerable to threats from abnormal examples, such as adversarial and backdoored examples constructed by attackers with malicious intentions as well as unintentionally mislabeled samples. Therefore, it is important and urgent to detect such abnormal examples. Although various detection approaches have been proposed respectively addressing some specific types of abnormal examples, they suffer from some limitations; until today, this problem is still of considerable interest. In this work, we first propose a novel characterization to distinguish abnormal examples from normal ones based on the observation that abnormal examples have significantly different (adversarial) robustness from normal ones. We systemically analyze those three different types of abnormal samples in terms of robustness and find that they have different characteristics from normal ones. As robustness measurement is computationally expensive and hence can be challenging to scale to large networks, we then propose to effectively and efficiently measure robustness of an input sample using the cost of adversarially attacking the input, which was originally proposed to test robustness of neural networks against adversarial examples. Next, we propose a novel detection method, named attack as detection (A 2 D for short), which uses the cost of adversarially attacking an input instead of robustness to check if it is abnormal. Our detection method is generic, and various adversarial attack methods could be leveraged. Extensive experiments show that A 2 D is more effective than recent promising approaches that were proposed to detect only one specific type of abnormal examples. We also thoroughly discuss possible adaptive attack methods to our adversarial example detection method and show that A 2 D is still effective in defending carefully designed adaptive adversarial attack methods—for example, the attack success rate drops to 0% on CIFAR10.
Förderung
- National Natural Science Foundation of China
- CAS Project for Young Scientists in Basic Research
- ISCAS New Cultivation Project
- Key Research and Development Program of Zhejiang
- Ministry of Education, Singapore, under its Academic Research Fund Tier 3
Zitieren
APA
Zhao, Z., Chen, G., Liu, T., Li, T., Song, F., Wang, J., & Sun, J. (2024). Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples. ACM Transactions on Software Engineering and Methodology, 33(3), 1-45. https://doi.org/10.1145/3631977
Vancouver
Zhao Z, Chen G, Liu T, Li T, Song F, Wang J, et al. Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples. ACM Transactions on Software Engineering and Methodology. 2024;33(3):1-45. doi:10.1145/3631977
BibTeX
@article{Zhao2024,
author = {Zhao, Zhe and Chen, Guangke and Liu, Tong and Li, Taishan and Song, Fu and Wang, Jingyi and Sun, Jun},
title = {Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2024},
volume = {33},
number = {3},
pages = {1--45},
doi = {10.1145/3631977}
}
EUVIMED