paper-with-me

홈 › Papers

Adversarial vulnerability for any classifier

2018-02-23 · NeurIPS 2018 12 · Alhussein Fawzi, Hamza Fawzi, Omar Fawzi

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the data is generated with a smooth generative model. We derive fundamental upper bounds on the robustness to perturbations of any classification function, and prove the existence of adversarial perturbations that transfer well across different classifiers with small risk. Our analysis of the robustness also provides insights onto key properties of generative models, such as their smoothness and dimensionality of latent space. We conclude with numerical experimental results showing that our bounds provide informative baselines to the maximal achievable robustness on several datasets.

📄 PDF Abstract BibTeX arXiv:1802.08686

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers

2021-02-09 · Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al.…

Defending Against Adversarial Examples by Regularized Deep Embedding

2019-09-25 · Yao Li, Martin Renqiang Min, Wenchao Yu, Cho-Jui Hsieh 외

Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples. Inspired by the observation that the intrinsic dimension of image data is much smaller than its pixel…

Adversarial AttackAdversarial Robustness

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-wise Adaptive Regularization Approach

2026-05-09 · Hira Nasir, Eiman Javed, Balawal Shabir, Zunera Jalil 외 arxiv

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversa…

Network Intrusion DetectionAdversarial RobustnessAdversarial Defense

Improving Robustness of Jet Tagging Algorithms with Adversarial Training

2022-03-25 · Annika Stein, Xavier Coubez, Spandan Mondal, Andrzej Novak 외

Deep learning is a standard tool in the field of high-energy physics, facilitating considerable sensitivity enhancements for numerous analysis strategies. In particular, in identification of physics objects, such as jet …

ClassificationJet Tagging

AI Classifiers Robustness to Adversarial Attacks: Manipulating Output of Classifiers by Small Input Perturbations

2020-06-20 · Thesis 2020 6 · Ghazi Gharsallah, Zhiying Wang

Deep Learning has shown an advanced performance in the state of the art applications in several domains. However, its vulnerability to adversarial attacks can remarkably ruin any powerful classifier's performance through…