paper-with-me

홈 › Papers

Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations

2020-10-28 · NeurIPS 2020 12 · Amit Daniely, Hadas Schacham

We consider ReLU networks with random weights, in which the dimension decreases at each layer. We show that for most such networks, most examples $x$ admit an adversarial perturbation at an Euclidean distance of $O\left(\frac{\|x\|}{\sqrt{d}}\right)$, where $d$ is the input dimension. Moreover, this perturbation can be found via gradient flow, as well as gradient descent with sufficiently small steps. This result can be seen as an explanation to the abundance of adversarial examples, and to the fact that they are found via gradient descent.

📄 PDF Abstract BibTeX arXiv:2010.14927

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

A Geometric Perspective on the Transferability of Adversarial Directions

2018-11-08 · Zachary Charles, Harrison Rosenberg, Dimitris Papailiopoulos

State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be e…

A New Family of Neural Networks Provably Resistant to Adversarial Attacks

2019-02-01 · Rakshit Agrawal, Luca de Alfaro, David Helmbold

Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified…

Boosting Gradient for White-Box Adversarial Attacks

2020-10-21 · Hongying Liu, Zhenyu Zhou, Fanhua Shang, Xiaoyu Qi 외

Deep neural networks (DNNs) are playing key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of studies have shown that there exist adve…

Blockingimage-classificationImage ClassificationObject Recognition

Neural Networks with Structural Resistance to Adversarial Attacks

2018-09-25 · ICLR 2019 5 · Luca de Alfaro

In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the un…

JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks

2019-04-07 · N. Benjamin Erichson, Zhewei Yao, Michael W. Mahoney

It has been demonstrated that very simple attacks can fool highly-sophisticated neural network architectures. In particular, so-called adversarial examples, constructed from perturbations of input data that are small or …