paper-with-me

Papers

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints

2021-02-25 · NeurIPS 2021 12 · Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio

Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current gradient-based attacks to be carefully tuned, initialized, and possibly executed for many computationally-demanding iterations, even if specialized to a given perturbation model. In this work, we overcome these limitations by proposing a fast minimum-norm (FMN) attack that works with different $\ell_p$-norm perturbation models ($p=0, 1, 2, \infty$), is robust to hyperparameter choices, does not require adversarial starting points, and converges within few lightweight steps. It works by iteratively finding the sample misclassified with maximum confidence within an $\ell_p$-norm constraint of size $\epsilon$, while adapting $\epsilon$ to minimize the distance of the current sample to the decision boundary. Extensive experiments show that FMN significantly outperforms existing attacks in terms of convergence speed and computation time, while reporting comparable or even smaller perturbation sizes.

📄 PDF Abstract BibTeX arXiv:2102.12827

Code (3)

pralab/Fast-Minimum-Norm-FMN-Attack 공식 구현 pytorch
bethgelab/foolbox tf
jeromerony/adversarial-library pytorch

Tasks

Adversarial AttackAdversarial Robustness

Methods 이 논문이 사용한 방법론

Fast Minimum-Norm Attack 설명 없음

Similar Papers 제목 키워드 기반

Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

2023-10-12 · Giuseppe Floris, Raffaele Mura, Luca Scionis, Giorgio Piras 외

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the…

Adversarial RobustnessHyperparameter Optimization

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks

2024-07-11 · Raffaele Mura, Giuseppe Floris, Luca Scionis, Giorgio Piras 외

Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size sch…

Adversarial RobustnessHyperparameter Optimization

$σ$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples

2024-02-02 · Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr 외

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investiga…

Adversarial Robustness

Towards Transferable Adversarial Perturbations with Minimum Norm

2021-06-18 · ICML Workshop AML 2021 7 · Fangcheng Liu, Chao Zhang, Hongyang Zhang

Transfer-based adversarial example is one of the most important classes of black-box attacks. Prior work in this direction often requires a fixed but large perturbation radius to reach a good transfer success rate. In th…

Model Selection

GSE: Group-wise Sparse and Explainable Adversarial Attacks

2023-11-29 · Shpresim Sadiku, Moritz Wagner, Sebastian Pokutta

Sparse adversarial attacks fool deep neural networks (DNNs) through minimal pixel perturbations, often regularized by the $\ell_0$ norm. Recent efforts have replaced this norm with a structural sparsity regularizer, such…