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

Source: [Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks](<https://www.sota2.com/research/paper/68fa66e81e209131cea13189>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:01:21.007Z

Authors: Thomas Brunner, Frederik Diehl, Alois Knoll

Published: 2019-06-14T09:17:19.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.06086>)

[PDF](<https://arxiv.org/pdf/1906.06086.pdf>)