# Attack as Defense: Characterizing Adversarial Examples using Robustness

Source: [Attack as Defense: Characterizing Adversarial Examples using Robustness](<https://www.sota2.com/research/paper/68fa697a1e209131cea224f8>)

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

Data updated: 2025-10-27T06:06:39.448Z

Authors: Zhe Zhao, Guangke Chen, Jingyi Wang, Yiwei Yang, Fu Song, Jun Sun

Published: 2021-03-13T06:29:13.000Z

## Abstract

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have been proposed to improve robustness of deep learning software, many of them are ineffective against adaptive attacks. In this work, we propose a novel characterization to distinguish adversarial examples from benign ones based on the observation that adversarial examples are significantly less robust than benign ones. As existing robustness measurement does not scale to large networks, we propose a novel defense framework, named attack as defense (A2D), to detect adversarial examples by effectively evaluating an example's robustness. A2D uses the cost of attacking an input for robustness evaluation and identifies those less robust examples as adversarial since less robust examples are easier to attack. Extensive experiment results on MNIST, CIFAR10 and ImageNet show that A2D is more effective than recent promising approaches. We also evaluate our defence against potential adaptive attacks and show that A2D is effective in defending carefully designed adaptive attacks, e.g., the attack success rate drops to 0% on CIFAR10.

## 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/2103.07633>)

[PDF](<https://arxiv.org/pdf/2103.07633.pdf>)
