论文信息 - Evaluating and Understanding the Robustness of Adversarial Logit Pairing

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models/claims considered, as well as a discussion of the methodology and results of our attack, which may offer insights into the reasons underlying the vulnerability of ALP to adversarial attack.

[1] Fabio Roli,et al. Evasion Attacks against Machine Learning at Test Time , 2013, ECML/PKDD.

[2] Dawn Xiaodong Song,et al. Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong , 2017, ArXiv.

[3] Nicholas Carlini,et al. On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses , 2018, ArXiv.

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

[5] Li Fei-Fei,et al. ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[6] David A. Wagner,et al. Defensive Distillation is Not Robust to Adversarial Examples , 2016, ArXiv.

[7] David A. Wagner,et al. MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples , 2017, ArXiv.

[8] Joan Bruna,et al. Intriguing properties of neural networks , 2013, ICLR.

[9] David Wagner,et al. Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods , 2017, AISec@CCS.

[10] Aleksander Madry,et al. Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[11] Pushmeet Kohli,et al. Adversarial Risk and the Dangers of Evaluating Against Weak Attacks , 2018, ICML.