# Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks

arXiv: https://arxiv.org/abs/1906.06086 · HTML: https://mlsanity.com/paper/1906.06086/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 3 of 3)

- [Out-of-Domain Robustness via Targeted Augmentations](https://mlsanity.com/paper/2302.11861/) (2023)
- [Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks](https://mlsanity.com/paper/2105.03251/) (2021)
- [Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition](https://mlsanity.com/paper/2209.04920/) (2022)

## Abstract (arXiv)

Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial, and that the performance of state-of-the-art attacks depends on it. First, we discuss desirable properties of starting points for attacking image classifiers, and how they can be chosen to increase query efficiency. Notably, we find that simply copying small patches from other images is a valid strategy. We then present an evaluation on ImageNet that clearly demonstrates the effectiveness of this method: Our initialization scheme reduces the number of queries required for a state-of-the-art Boundary Attack by 81%, significantly outperforming previous results reported for targeted black-box adversarial examples.