paper-with-me

Papers

Sparsity-based Defense against Adversarial Attacks on Linear Classifiers

2018-01-15 · Zhinus Marzi, Soorya Gopalakrishnan, Upamanyu Madhow, Ramtin Pedarsani

Deep neural networks represent the state of the art in machine learning in a growing number of fields, including vision, speech and natural language processing. However, recent work raises important questions about the robustness of such architectures, by showing that it is possible to induce classification errors through tiny, almost imperceptible, perturbations. Vulnerability to such "adversarial attacks", or "adversarial examples", has been conjectured to be due to the excessive linearity of deep networks. In this paper, we study this phenomenon in the setting of a linear classifier, and show that it is possible to exploit sparsity in natural data to combat $\ell_{\infty}$-bounded adversarial perturbations. Specifically, we demonstrate the efficacy of a sparsifying front end via an ensemble averaged analysis, and experimental results for the MNIST handwritten digit database. To the best of our knowledge, this is the first work to show that sparsity provides a theoretically rigorous framework for defense against adversarial attacks.

📄 PDF Abstract BibTeX arXiv:1801.04695

Code (3)

soorya19/sparsity-based-defenses 공식 구현 tf
ZhinusMarzi/Adversarial-attack tf
ZhinusMarzi/Sparsity-based-defenses-against-adversarial-attacks tf

Similar Papers 제목 키워드 기반

Robust Adversarial Learning via Sparsifying Front Ends

2018-10-24 · Soorya Gopalakrishnan, Zhinus Marzi, Metehan Cekic, Upamanyu Madhow 외

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks. In this paper, we take a bottom-up signal processing perspective to this problem and show that a syst…

Combating Adversarial Attacks Using Sparse Representations

2018-03-11 · Soorya Gopalakrishnan, Zhinus Marzi, Upamanyu Madhow, Ramtin Pedarsani

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 to…

General Classification

How many perturbations break this model? Evaluating robustness beyond adversarial accuracy

2022-07-08 · Raphael Olivier, Bhiksha Raj

Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbati…

Adversarial AttackAdversarial RobustnessData Augmentation

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks

2021-05-18 · NeurIPS 2021 12 · Dequan Wang, An Ju, Evan Shelhamer, David Wagner 외

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses…

Generative Cleaning Networks with Quantized Nonlinear Transform for Deep Neural Network Defense

2019-09-25 · Jianhe Yuan, Zhihai He

Effective defense of deep neural networks against adversarial attacks remains a challenging problem, especially under white-box attacks. In this paper, we develop a new generative cleaning network with quantized nonline…