# L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks

arXiv: https://arxiv.org/abs/2401.15335 · HTML: https://mlsanity.com/paper/2401.15335/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Efficient Decision-based Black-box Adversarial Attacks on Face Recognition](https://mlsanity.com/paper/1904.04433/) (2019)
- [Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving](https://mlsanity.com/paper/1907.06826/) (2019)
- [AutoML-Zero: Evolving Machine Learning Algorithms From Scratch](https://mlsanity.com/paper/2003.03384/) (2020)
- [Chip-Chat: Challenges and Opportunities in Conversational Hardware Design](https://mlsanity.com/paper/2305.13243/) (2023)
- [Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach](https://mlsanity.com/paper/1807.04457/) (2018)
- [Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap](https://mlsanity.com/paper/2401.10034/) (2024)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [Generalizable Black-Box Adversarial Attack with Meta Learning](https://mlsanity.com/paper/2301.00364/) (2023)
- [Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks](https://mlsanity.com/paper/2303.06280/) (2023)
- [PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks](https://mlsanity.com/paper/2401.10586/) (2024)

## Built on by (most cited first, 8 of 8)

- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning](https://mlsanity.com/paper/2405.00705/) (2024)
- [EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models](https://mlsanity.com/paper/2510.03760/) (2025)
- [A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving](https://mlsanity.com/paper/2509.08269/) (2025)
- [MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework](https://mlsanity.com/paper/2501.07251/) (2025)
- [Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models](https://mlsanity.com/paper/2509.14265/) (2025)
- [Relation Reasoning with LLMs in Expensive Optimization](https://mlsanity.com/paper/2605.02933/) (2026)
- [ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors](https://mlsanity.com/paper/2607.15246/) (2026)

## Abstract (arXiv)

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed probabilities or scores, are particularly insidious and difficult to defend against. This work introduces L-AutoDA (Large Language Model-based Automated Decision-based Adversarial Attacks), a novel approach leveraging the generative capabilities of Large Language Models (LLMs) to automate the design of these attacks. By iteratively interacting with LLMs in an evolutionary framework, L-AutoDA automatically designs competitive attack algorithms efficiently without much human effort. We demonstrate the efficacy of L-AutoDA on CIFAR-10 dataset, showing significant improvements over baseline methods in both success rate and computational efficiency. Our findings underscore the potential of language models as tools for adversarial attack generation and highlight new avenues for the development of robust AI systems.