paper-with-me

홈 › Papers

Attacking Adversarial Defences by Smoothing the Loss Landscape

2022-08-01 · Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate. A common, but not universal, way to achieve this effect is via the use of stochastic neural networks. We show that this is a form of gradient obfuscation, and propose a general extension to gradient-based adversaries based on the Weierstrass transform, which smooths the surface of the loss function and provides more reliable gradient estimates. We further show that the same principle can strengthen gradient-free adversaries. We demonstrate the efficacy of our loss-smoothing method against both stochastic and non-stochastic adversarial defences that exhibit robustness due to this type of obfuscation. Furthermore, we provide analysis of how it interacts with Expectation over Transformation; a popular gradient-sampling method currently used to attack stochastic defences.

📄 PDF Abstract BibTeX arXiv:2208.00862

Code (1)

peustr/wt-pgd 공식 구현 pytorch

Tasks

Navigate

Similar Papers 제목 키워드 기반

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

2021-06-05 · ICCV 2021 10 · Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised lear…

Domain AdaptationUnsupervised Domain Adaptation

LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate

2023-12-20 · Tao Wu, Tie Luo, Donald C. Wunsch

The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks. Previous works for generating transferable adversarial examples focus on attacking \emph{given} pretra…

Adversarial Robustness

Preventing Adversarial AI Attacks Against Autonomous Situational Awareness: A Maritime Case Study

2025-05-27 · Mathew J. Walter, Aaron Barrett, Kimberly Tam

Adversarial artificial intelligence (AI) attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and man…

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences

2024-06-14 · Saiyue Lyu, Shadab Shaikh, Frederick Shpilevskiy, Evan Shelhamer 외

We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to …

Adversarial Robustnessimage-classificationImage Classification

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

2022-09-13 · Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein 외

Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentat…

image-classificationImage ClassificationSegmentationSemantic Segmentation