# Square Attack: a query-efficient black-box adversarial attack via random search

arXiv: https://arxiv.org/abs/1912.00049 · HTML: https://mlsanity.com/paper/1912.00049/

## Key facts

- Cited by 685 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2019.

## Built on by (most cited first, 30 of 685)

- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Fixing Data Augmentation to Improve Adversarial Robustness](https://mlsanity.com/paper/2103.01946/) (2021)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [Are Transformers More Robust Than CNNs?](https://mlsanity.com/paper/2111.05464/) (2021)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [Open Sesame! Universal Black Box Jailbreaking of Large Language Models](https://mlsanity.com/paper/2309.01446/) (2023)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Anti-DreamBooth: Protecting users from personalized text-to-image synthesis](https://mlsanity.com/paper/2303.15433/) (2023)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [LAS-AT: Adversarial Training with Learnable Attack Strategy](https://mlsanity.com/paper/2203.06616/) (2022)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [Adversarial Sticker: A Stealthy Attack Method in the Physical World](https://mlsanity.com/paper/2104.06728/) (2021)
- [Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks](https://mlsanity.com/paper/2110.12976/) (2021)
- [Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection](https://mlsanity.com/paper/2210.00875/) (2022)
- [Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better](https://mlsanity.com/paper/2108.07969/) (2021)
- [RobustART: Benchmarking Robustness on Architecture Design and Training Techniques](https://mlsanity.com/paper/2109.05211/) (2021)
- [Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection](https://mlsanity.com/paper/2201.08970/) (2022)
- [Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models](https://mlsanity.com/paper/2303.01870/) (2023)
- [A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion](https://mlsanity.com/paper/2303.16378/) (2023)
- [On Improving Adversarial Transferability of Vision Transformers](https://mlsanity.com/paper/2106.04169/) (2021)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Robust Evaluation of Diffusion-Based Adversarial Purification](https://mlsanity.com/paper/2303.09051/) (2023)
- [Evaluating the Adversarial Robustness of Adaptive Test-time Defenses](https://mlsanity.com/paper/2202.13711/) (2022)
- [A Light Recipe to Train Robust Vision Transformers](https://mlsanity.com/paper/2209.07399/) (2022)
- [When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture](https://mlsanity.com/paper/2210.07540/) (2022)
- [Black Box Adversarial Prompting for Foundation Models](https://mlsanity.com/paper/2302.04237/) (2023)
- [Structure Invariant Transformation for better Adversarial Transferability](https://mlsanity.com/paper/2309.14700/) (2023)
- [A Unified Algebraic Perspective on Lipschitz Neural Networks](https://mlsanity.com/paper/2303.03169/) (2023)

## Abstract (arXiv)

We propose the Square Attack, a score-based black-box l2- and l_∞-adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. Square Attack is based on a randomized search scheme which selects localized square-shaped updates at random positions so that at each iteration the perturbation is situated approximately at the boundary of the feasible set. Our method is significantly more query efficient and achieves a higher success rate compared to the state-of-the-art methods, especially in the untargeted setting. In particular, on ImageNet we improve the average query efficiency in the untargeted setting for various deep networks by a factor of at least 1.8 and up to 3 compared to the recent state-of-the-art l_∞-attack of Al-Dujaili & O'Reilly. Moreover, although our attack is black-box, it can also outperform gradient-based white-box attacks on the standard benchmarks achieving a new state-of-the-art in terms of the success rate. The code of our attack is available at https://github.com/max-andr/square-attack.