Fetching the paper…

Reading the bibliography…

2018

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

Engstrom, Logan, Ilyas, Andrew, Athalye, Anish

Original
PDF
Post on X

Understand

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.

Evaluating and Understanding the Robustness of Adversarial Logit Pairing · Around

Built on

Imagenet: A large-scale hierarchical image database
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009
Earlier work this paper cites.
Evasion attacks against machine learning at test time
B. Biggio, I. Corona, D. Maiorca, B. Nelson, N. Šrndić, P. Laskov, G. Giacinto, and F. Roli · 2013
Earlier work this paper cites.
Intriguing properties of neural networks
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus · 2013
Earlier work this paper cites.

Similar

Defensive distillation is not robust to adversarial examples
Original
N. Carlini and D. Wagner · 2016
Cited alongside, same era.
Adversarial example defenses: Ensembles of weak defenses are not strong
Original
W. He, J. Wei, X. Chen, N. Carlini, and D. Song · 2017
Cited alongside, same era.
On the robustness of the CVPR 2018 white-box adversarial example defenses
Original
A. Athalye and N. Carlini · 2018
Cited alongside, same era.
Adversarial examples are not easily detected: Bypassing ten detection methods
N. Carlini and D. Wagner
Cited in the paper.
Magnet and “efficient defenses against adversarial attacks” are not robust to adversarial examples
Original
N. Carlini and D. Wagner
Cited in the paper.
Adversarial logit pairing
Original
H. Kannan, A. Kurakin, and I. Goodfellow
Cited in the paper.
Towards deep learning models resistant to adversarial attacks
Original
A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu
Cited in the paper.

Then

Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Original
A. Athalye, N. Carlini, and D. Wagner · 2018
Closest in time.
Adversarial risk and the dangers of evaluating against weak attacks
Original
J. Uesato, B. O’Donoghue, A. van den Oord, and P. Kohli · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…