MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
This work addresses the inefficiency of crossover in evolutionary adversarial attacks for security researchers, offering a more effective attack method that also reveals geometric properties of adversarial examples.
MoCo-EA introduces a Bézier crossover operator for evolutionary adversarial attacks, exploiting mode connectivity in adversarial space to improve attack efficiency and transferability. It achieves higher success rates and faster convergence than traditional genetic operations.
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 Bézier crossover operator that optimizes perturbations along a continuous Bézier 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) Bézier 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.