MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks

TL;DR

MoCo-EA introduces a novel Bézier crossover operator in evolutionary adversarial attacks, exploiting the connected manifold structure of adversarial examples to improve efficiency and transferability.

Contribution

It proposes a path-based crossover method that enhances evolutionary attack efficiency by leveraging the geometric structure of adversarial spaces.

Findings

Adversarial examples lie on connected manifolds.

Intermediate points along optimized paths have higher transferability.

Bézier crossover outperforms traditional genetic operations in efficiency.

Abstract

Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover operations that destroy adversarial properties through discrete interpolation. We introduce Mode Connectivity Evolutionary Attack (MoCo-EA), which replaces traditional crossover with a novel B\'ezier crossover operator that optimizes perturbations along a continuous B\'ezier curve between parent perturbations. Our key insight is that adversarial examples lie on connected manifolds where intermediate points maintain and often enhance attack effectiveness. We demonstrate three findings: (1) Successful adversarial perturbations exhibit mode connectivity; (2) Intermediate points along optimized paths achieve higher transferability than endpoints; (3) B\'ezier crossover dramatically outperforms discrete genetic operations while reducing convergence time and query requirements. By exploiting the geometric structure of adversarial space through path optimization, MoCo-EA provides an efficient and reliable method. Our work challenges the traditional view of adversarial examples as isolated points and opens new directions for both attack generation and defense research.