Fetching the paper…

Reading the bibliography…

2018

Bypassing Feature Squeezing by Increasing Adversary Strength

Sharma, Yash, Chen, Pin-Yu

Original
PDF
Post on X

Understand

Feature Squeezing is a recently proposed defense method which reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample.

It has been shown that feature squeezing defenses can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.
However, we demonstrate on the MNIST and CIFAR-10 datasets that by increasing the adversary strength of said state-of-the-art attacks, one can bypass the detection framework with adversarial examples of minimal visual distortion.
These results suggest for proposed defenses to validate against stronger attack configurations.

Bypassing Feature Squeezing by Increasing Adversary Strength · Around

Built on

A fast iterative shrinkage-thresholding algorithm for linear inverse problems
A. Beck and M. Teboulle · 2009
Earlier work this paper cites.
Intriguing properties of neural networks
Original
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
D. Kingma and J. Ba · 2014
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Original
I. Goodfellow, J. Shlens, and C. Szegedy · 2015
Earlier work this paper cites.

Similar

Adversarial machine learning at scale
Original
A. Kurakin, I. Goodfellow, and S. Bengio · 2016
Cited alongside, same era.
Delving into transferable adversarial examples and black-box attacks
Original
Y. Liu, X. Chen, C. Liu, and D. Song · 2016
Cited alongside, same era.
Transferability in machine learning: from phenomena to black-box attacks using adversarial samples
Original
Nicolas Papernot, Patrick McDaniel, and Ian Goodfellow · 2016
Cited alongside, same era.
Towards evaluating the robustness of neural networks
N. Carlini and D. Wagner · 2017
Cited alongside, same era.

Then

Ead: Elastic-net attacks to deep neural networks via adversarial examples
Original
P.Y. Chen, Y. Sharma, H. Zhang, J. Yi, and C.J. Hsieh · 2017
Later among the works it cites.
Attacking the madry defense model with l1-based adversarial examples
Original
Y. Sharma and P. Y. Chen · 2017
Later among the works it cites.
Ensemble adversarial training: Attacks and defenses
Original
F. Tramèr, A. Kurakin, N. Papernot, D. Boneh, and P. McDaniel · 2017
Later among the works it cites.
Feature squeezing: Detecting adversarial examples in deep neural networks
Original
W. Xu, D. Evans, and Y. Qi · 2017
Later among the works it cites.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…