Benchmarking Adversarial Robustness

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance to perform correct and complete evaluations of the adversarial attack and defense algorithms. In this paper, we establish a comprehensive, rigorous, and coherent benchmark to evaluate adversarial robustness on image classification tasks. After briefly reviewing plenty of representative attack and defense methods, we perform large-scale experiments with two robustness curves as the fair-minded evaluation criteria to fully understand the performance of these methods. Based on the evaluation results, we draw several important findings and provide insights for future research.

[1]  Harini Kannan,et al.  Adversarial Logit Pairing , 2018, NIPS 2018.

[2]  Aleksander Madry,et al.  On Evaluating Adversarial Robustness , 2019, ArXiv.

[3]  Matthias Bethge,et al.  Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models , 2017, ArXiv.

[4]  Ning Chen,et al.  Improving Adversarial Robustness via Promoting Ensemble Diversity , 2019, ICML.

[5]  David A. Wagner,et al.  Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples , 2018, ICML.

[6]  Aditi Raghunathan,et al.  Semidefinite relaxations for certifying robustness to adversarial examples , 2018, NeurIPS.

[7]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[8]  Matthias Bethge,et al.  Adversarial Vision Challenge , 2018, The NeurIPS '18 Competition.

[9]  Dawn Xiaodong Song,et al.  Decision Boundary Analysis of Adversarial Examples , 2018, ICLR.

[10]  Nicholas Carlini.  A critique of the DeepSec Platform for Security Analysis of Deep Learning Models , 2019, ArXiv.

[11]  J. Zico Kolter,et al.  Scaling provable adversarial defenses , 2018, NeurIPS.

[12]  Martin Wistuba,et al.  Adversarial Robustness Toolbox v1.0.0 , 2018, 1807.01069.

[13]  Ian J. Goodfellow,et al.  Technical Report on the CleverHans v2.1.0 Adversarial Examples Library , 2016 .

[14]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[15]  Cho-Jui Hsieh,et al.  Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network , 2018, ICLR.

[16]  Matthias Bethge,et al.  Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models , 2017, ICLR.

[17]  Zoubin Ghahramani,et al.  A study of the effect of JPG compression on adversarial images , 2016, ArXiv.

[18]  Jun Zhu,et al.  Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Rama Chellappa,et al.  Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models , 2018, ICLR.

[20]  Ananthram Swami,et al.  Practical Black-Box Attacks against Machine Learning , 2016, AsiaCCS.

[21]  Yang Song,et al.  Constructing Unrestricted Adversarial Examples with Generative Models , 2018, NeurIPS.

[22]  Yao Zhao,et al.  Adversarial Attacks and Defences Competition , 2018, ArXiv.