# Adversarial Example Generation using Evolutionary Multi-objective Optimization

arXiv: https://arxiv.org/abs/2001.05844 · HTML: https://mlsanity.com/paper/2001.05844/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2019.

## Built on by (most cited first, 9 of 9)

- [Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2201.00768/) (2022)
- [Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization](https://mlsanity.com/paper/2111.01528/) (2021)
- [Effective Universal Unrestricted Adversarial Attacks using a MOE Approach](https://mlsanity.com/paper/2103.00250/) (2021)
- [Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization](https://mlsanity.com/paper/2101.07512/) (2021)
- [Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume](https://mlsanity.com/paper/2403.05100/) (2024)
- [Generating Adversarial Examples with Task Oriented Multi-Objective Optimization](https://mlsanity.com/paper/2304.13229/) (2023)
- [Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems](https://mlsanity.com/paper/2406.07811/) (2024)
- [PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack](https://mlsanity.com/paper/2101.07538/) (2021)
- [MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework](https://mlsanity.com/paper/2501.07251/) (2025)

## Abstract (arXiv)

This paper proposes Evolutionary Multi-objective Optimization (EMO)-based Adversarial Example (AE) design method that performs under black-box setting. Previous gradient-based methods produce AEs by changing all pixels of a target image, while previous EC-based method changes small number of pixels to produce AEs. Thanks to EMO's property of population based-search, the proposed method produces various types of AEs involving ones locating between AEs generated by the previous two approaches, which helps to know the characteristics of a target model or to know unknown attack patterns. Experimental results showed the potential of the proposed method, e.g., it can generate robust AEs and, with the aid of DCT-based perturbation pattern generation, AEs for high resolution images.