Exploring Robustness under New Adversarial Threats: A Comprehensive Analysis of Deep Neural Network Defenses
Pages 206 - 210
Abstract
Although various methods have been proposed to improve the robustness of deep neural network models, evaluating these models in a fair and reasonable manner remains a challenge. Existing evaluation methods often consider only limited types of attacks, ignoring the generalization performance against new types of attacks, and fail to cover the most advanced defense models. To address these issues, we propose a unified framework to evaluate model robustness under different types of attacks. This framework integrates non-Lp and Lp attacks, and comprehensively evaluates the robustness of various advanced robust models on the CIFAR-10 and ImageNet subsets. Experimental results show that even the most advanced defense models exhibit vulnerabilities under certain new types of attacks, highlighting the importance of developing more comprehensive robustness benchmarks and providing guidance for the design of future robust deep learning models.
References
[1]
Max Kaufmann, Daniel Kang, Yi Sun, Steven Basart, Xuwang Yin, Mantas Mazeika, Akul Arora, Adam Dziedzic, Franziska Boenisch, Tom Brown, Jacob Steinhardt, and Dan Hendrycks. 2019. Testing Robustness Against Unforeseen Adversaries. arXiv:1908.08016. Retrieved from http://arxiv.org/abs/1908.08016.
[2]
Jiashuo Liu, Zheyan Shen, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, and Peng Cui. 2021. Towards Out-Of-Distribution Generalization: A Survey. arXiv:2108.13624. Retrieved from http://arxiv.org/abs/2108.13624.
[3]
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In Proceedings of the 2nd International Conference on Learning Representations (ICLR'14).
[4]
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In Proceedings of the 6th International Conference on Learning Representations (ICLR'18).
[5]
Dongxian Wu, Shu-Tao Xia, and Yisen Wang. 2020. Adversarial weight perturbation helps robust generalization. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS'20). Curran Associates Inc., Red Hook, NY, USA, 2958–2969.
[6]
Leslie Rice, Eric Wong, and J. Zico Kolter. 2020. Overfitting in adversarially robust deep learning. In Proceedings of the 37th International Conference on Machine Learning (ICML'20). ACM Inc., New York, NY, 8093–8104.
[7]
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, and Aleksander Madry. 2018. Adversarially robust generalization requires more data. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS'18). Curran Associates Inc., Red Hook, NY, USA, 5019–5031.
[8]
Cassidy Laidlaw and Soheil Feizi. 2019. Functional adversarial attacks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS'19). Curran Associates Inc., Red Hook, NY, USA, 10408–10418.
[9]
Chaowei Xiao, Jun-Yan Zhu, Bo Li, Warren He, Mingyan Liu, and Dawn Song. 2018. Spatially Transformed Adversarial Examples. In Proceedings of the 6th International Conference on Learning Representations (ICLR'18).
[10]
Xiang Ling, Shouling Ji, Jiaxu Zou, Jiannan Wang, Chunming Wu, Bo Li, and Ting Wang. 2019. DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model. In Proceedings of the 40th IEEE Symposium on Security and Privacy (S&P'19), 673–690. https://doi.org/10.1109/SP.2019.00023.
[11]
Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, and Patrick McDaniel. 2018. Technical Report on the CleverHans v2.1.0 Adversarial Examples Library. arXiv:1610.00768. Retrieved from http://arxiv.org/abs/1610.00768.
[12]
Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, and Matthias Hein. 2021. RobustBench: a standardized adversarial robustness benchmark. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021). Curran Associates Inc., Red Hook, NY, USA.
[13]
Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, Alan Yuille, Philip H. S. Torr, and Dacheng Tao. 2021. RobustART: Benchmarking Robustness on Architecture Design and Training Techniques. arXiv:2109.05211. Retrieved from http://arxiv.org/abs/2109.05211.
[14]
Chang Liu, Yinpeng Dong, Wenzhao Xiang, Xiao Yang, Hang Su, Jun Zhu, Yuefeng Chen, Yuan He, Hui Xue, and Shibao Zheng. 2023. A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking. arXiv:2302.14301. Retrieved from http://arxiv.org/abs/2302.14301.
[15]
Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, and Tsung-Yi Ho. 2022. CARBEN: Composite Adversarial Robustness Benchmark. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI'22), 5908–5911. https://doi.org/10.24963/ijcai.2022/851.
[16]
Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, and Prateek Mittal. 2023. MultiRobustBench: benchmarking robustness against multiple attacks. In Proceedings of the 40th International Conference on Machine Learning (ICML'23). ACM Inc., New York, NY, 6760–6785.
[17]
Jonas Rauber, Wieland Brendel, and Matthias Bethge. 2017. Foolbox: A Python toolbox to benchmark the robustness of machine learning models. arXiv:1707.04131. Retrieved from http://arxiv.org/abs/1707.04131.
[18]
Maria-Irina Nicolae, Mathieu Sinn, Minh Ngoc Tran, Beat Buesser, Ambrish Rawat, Martin Wistuba, Valentina Zantedeschi, Nathalie Baracaldo, Bryant Chen, Heiko Ludwig, Ian M. Molloy, and Ben Edwards. 2018. Adversarial Robustness Toolbox v1.0.0. arXiv: 1807.01069. Retrieved from http://arxiv.org/abs/1807.01069.
[19]
Cassidy Laidlaw, Sahil Singla, and Soheil Feizi. 2021. Perceptual Adversarial Robustness: Defense Against Unseen Threat Models. In Proceedings of the 9th International Conference on Learning Representations (ICLR'21).
[20]
Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, and Aleksander Madry. 2019. Exploring the Landscape of Spatial Robustness. In Proceedings of the 36th International Conference on Machine Learning (ICML'19). ACM Inc., New York, NY, 1802–1811.
[21]
Danny Karmon, Daniel Zoran, and Yoav Goldberg. 2018. LaVAN: Localized and Visible Adversarial Noise. In Proceedings of the 35th International Conference on Machine Learning (ICML'18). ACM Inc., New York, NY, 2507–2515.
[22]
Sihui Dai, Saeed Mahloujifar, and Prateek Mittal. 2022. Formulating Robustness Against Unforeseen Attacks. In Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS'22). Curran Associates Inc., Red Hook, NY, USA, 8647–8661.
[23]
Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, and Tsung-Yi Ho. 2023. Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'23), 24658–24667. https://doi.org/10.1109/CVPR52729.2023.02362.
[24]
Zekai Wang, Tianyu Pang, Chao Du, Min Lin, Weiwei Liu, and Shuicheng Yan. 2023. Better diffusion models further improve adversarial training. In Proceedings of the 40th International Conference on Machine Learning (ICML'23). ACM Inc., New York, NY, 36246–36263.
Index Terms
- Exploring Robustness under New Adversarial Threats: A Comprehensive Analysis of Deep Neural Network Defenses
Recommendations
Hardening Interpretable Deep Learning Systems: Investigating Adversarial Threats and Defenses
Deep learning methods have gained increasing attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given task, ...
Adversarial robustness improvement for deep neural networks
AbstractDeep neural networks (DNNs) are key components for the implementation of autonomy in systems that operate in highly complex and unpredictable environments (self-driving cars, smart traffic systems, smart manufacturing, etc.). It is well known that ...
Adversarial attacks and defenses in deep learning for image recognition: A survey
Highlights- Introducing the concepts of adversarial examples and adversarial learning.
- ...
AbstractIn recent years, researches on adversarial attacks and defense mechanisms have obtained much attention. It’s observed that adversarial examples crafted with small malicious perturbations would mislead the deep neural network (DNN) ...
Comments
Information & Contributors
Information
Published In
May 2024
439 pages
ISBN:9798400709562
DOI:10.1145/3665348
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 03 July 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
GAIIS 2024
GAIIS 2024: 2024 International Conference on Generative Artificial Intelligence and Information Security
May 10 - 12, 2024
Kuala Lumpur, Malaysia
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 12Total Downloads
- Downloads (Last 12 months)12
- Downloads (Last 6 weeks)3
Reflects downloads up to 27 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format