Understand
It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs).
- In this paper, we make the case that sparse representations of the input data are a crucial tool for combating such attacks.
- For linear classifiers, we show that a sparsifying front end is provably effective against $\ell_{\infty}$-bounded attacks, reducing output distortion due to the attack by a factor of roughly $K / N$ where $N$ is the data dimension and $K$ is the sparsity level.
- We then extend this concept to DNNs, showing that a "locally linear" model can be used to develop a theoretical foundation for crafting attacks and defenses.
Built on
Biorthogonal bases of compactly supported wavelets
Albert Cohen, Ingrid Daubechies, and J-C Feauveau · 1992
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner · 1998
Earlier work this paper cites.
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus · 2014
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy · 2015
Earlier work this paper cites.
Neural Networks and Deep Learning
Michael A Nielsen · 2015
Earlier work this paper cites.
Similar
DeepFool: A simple and accurate method to fool deep neural networks
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard · 2016
Cited alongside, same era.
Exponential expressivity in deep neural networks through transient chaos
Ben Poole, Subhaneil Lahiri, Maithra Raghu, Jascha Sohl-Dickstein, and Surya Ganguli · 2016
Cited alongside, same era.
Enhancing robustness of machine learning systems via data transformations
Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, and Prateek Mittal · 2017
Cited alongside, same era.
Keeping the bad guys out: Protecting and vaccinating deep learning with JPEG compression
Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Fred Hohman, Li Chen, Michael E Kounavis, and Duen Horng Chau · 2017
Cited alongside, same era.
Classification regions of deep neural networks
Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, and Stefano Soatto · 2017
Cited alongside, same era.
Then
The robust manifold defense: Adversarial training using generative models
Andrew Ilyas, Ajil Jalal, Eirini Asteri, Constantinos Daskalakis, and Alexandros G Dimakis · 2017
Later among the works it cites.
Countering adversarial images using input transformations
Chuan Guo, Mayank Rana, Moustapha Cisse, and Laurens van der Maaten · 2018
Closest in time.
Sparsity-based defense against adversarial attacks on linear classifiers
Zhinus Marzi, Soorya Gopalakrishnan, Upamanyu Madhow, and Ramtin Pedarsani · 2018
Closest in time.
Defense-GAN: Protecting classifiers against adversarial attacks using generative models
Pouya Samangouei, Maya Kabkab, and Rama Chellappa · 2018
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…