paper-with-me

홈 › Papers

Bayesian Inference with Certifiable Adversarial Robustness

2021-02-10 · Matthew Wicker, Luca Laurenti, Andrea Patane, Zhoutong Chen, Zheng Zhang, Marta Kwiatkowska

We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. We rely on techniques from constraint relaxation of non-convex optimisation problems and modify the standard cross-entropy error model to enforce posterior robustness to worst-case perturbations in $\epsilon$-balls around input points. We illustrate how the resulting framework can be combined with methods commonly employed for approximate inference of BNNs. In an empirical investigation, we demonstrate that the presented approach enables training of certifiably robust models on MNIST, FashionMNIST and CIFAR-10 and can also be beneficial for uncertainty calibration. Our method is the first to directly train certifiable BNNs, thus facilitating their deployment in safety-critical applications.

📄 PDF Abstract BibTeX arXiv:2102.05289

Code (1)

matthewwicker/CertifiableBayesianInference 공식 구현 tf

Tasks

Adversarial RobustnessBayesian Inference

Similar Papers 제목 키워드 기반

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses

2023-10-19 · Chong Xiang, Tong Wu, Sihui Dai, Jonathan Petit 외

State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x…

Towards Certifiable Adversarial Sample Detection

2020-02-20 · Ilia Shumailov, Yiren Zhao, Robert Mullins, Ross Anderson

Convolutional Neural Networks (CNNs) are deployed in more and more classification systems, but adversarial samples can be maliciously crafted to trick them, and are becoming a real threat. There have been various proposa…

Adversarial Robustness

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches

2025-05-30 · CVPR 2025 1 · Dennis Jacob, Chong Xiang, Prateek Mittal

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically re…

Binary ClassificationClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Second-Order Adversarial Attack and Certifiable Robustness

2019-05-01 · ICLR 2019 5 · Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin

Adversarial training has been recognized as a strong defense against adversarial attacks. In this paper, we propose a powerful second-order attack method that reduces the accuracy of the defense model by Madry et al. (20…

Adversarial Attack

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing

2021-03-30 · Cheng Chen, Bhavya Kailkhura, Ryan Goldhahn, Yi Zhou

Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks. Although several heuristic defenses are proposed to enhance the robustness of federated…

Federated Learning