paper-with-me

Papers

Adversarial attacks for mixtures of classifiers

2023-07-20 · Lucas Gnecco Heredia, Benjamin Negrevergne, Yann Chevaleyre

Mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, it has been shown that existing attacks are not well suited for this kind of classifiers. In this paper, we discuss the problem of attacking a mixture in a principled way and introduce two desirable properties of attacks based on a geometrical analysis of the problem (effectiveness and maximality). We then show that existing attacks do not meet both of these properties. Finally, we introduce a new attack called lattice climber attack with theoretical guarantees on the binary linear setting, and we demonstrate its performance by conducting experiments on synthetic and real datasets.

📄 PDF Abstract BibTeX arXiv:2307.10788

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifiers

2025-06-12 · Lucas Gnecco-Heredia, Benjamin Negrevergne, Yann Chevaleyre

Finite mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, existing attacks have been shown to not suit this kind of classifier. I…

GEOMETRIC AUGMENTATION FOR ROBUST NEURAL NETWORK CLASSIFIERS

2019-05-01 · ICLR 2019 5 · Robert M. Taylor, Yusong Tan

We introduce a novel geometric perspective and unsupervised model augmentation framework for transforming traditional deep (convolutional) neural networks into adversarially robust classifiers. Class-conditional probabil…

General ClassificationTime SeriesTime Series Analysis

Explainable Adversarial Attacks on Coarse-to-Fine Classifiers

2025-01-19 · Akram Heidarizadeh, Connor Hatfield, Lorenzo Lazzarotto, HanQin Cai 외

Traditional adversarial attacks typically aim to alter the predicted labels of input images by generating perturbations that are imperceptible to the human eye. However, these approaches often lack explainability. Moreov…

Automated Adversarial Discovery for Safety Classifiers

2024-06-24 · Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha, Yao Qin 외

Safety classifiers are critical in mitigating toxicity on online forums such as social media and in chatbots. Still, they continue to be vulnerable to emergent, and often innumerable, adversarial attacks. Traditional aut…

Diversity

Adversarial Examples for Cost-Sensitive Classifiers

2019-10-04 · Gavin S. Hartnett, Andrew J. Lohn, Alexander P. Sedlack

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the u…