Aug 22, 2024 · To bridge this gap, this paper introduces a framework for adversarial attacks on evolutionary algorithms aimed at countering both single- ...

To satisfy the requirement of attack effect and imperceptibility, SparseEA is adopted as the attack algorithm. The experimental results on attacking multiple ...

Apr 19, 2022 · This work proposes an imperceivable and sparse adversarial attack method, on the basis of a new coevolutionary algorithm.

The sparse adversarial attack has attracted increasing attention due to the merit of a low attack cost via changing a small number of pixels.

Apr 13, 2022 · To achieve imperceptible and sparse adversarial attacks, this paper formulates a bi-objective constrained optimization problem simultaneously ...

Our algorithm draws inspiration from evolutionary computation and incorporates a mechanism for prioritizing objectives that aligns with an attacker's goals. Our ...

Abstract—The sparse adversarial attack has attracted in- creasing attention due to the merit of a low attack cost via changing a small number of pixels.

Sparse adversarial attacks can fool deep neural networks (DNNs) by only perturbing a few pixels. (regularized by `0 norm). Recent efforts combine.

We propose a transfer-based sparse attack method, called adaptive momentum variance based iterative gradient method with a class activation map.

Imperceptible and Sparse Adversarial Attacks via a Dual-Population-Based Constrained Evolutionary Algorithm - University of Surrey - Journal article.