# Smooth Adversarial Examples

## TL;DR

This paper introduces a novel smoothing technique for adversarial examples that adapts to image content, improving visual quality while maintaining attack success rates with lower distortion.

## Contribution

It proposes a content-aware Laplacian smoothing method for adversarial perturbations, enhancing visual quality without sacrificing attack effectiveness.

## Key findings

- Smoothing improves visual quality of adversarial examples.
- Attack success rate remains high despite smoothing constraints.
- Lower distortion levels are achieved with the proposed method.

## Abstract

This paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artefacts. In this work, smoothing has a different meaning as it perceptually shapes the perturbation according to the visual content of the image to be attacked. The perturbation becomes locally smooth on the flat areas of the input image, but it may be noisy on its textured areas and sharp across its edges. This operation relies on Laplacian smoothing, well-known in graph signal processing, which we integrate in the attack pipeline. We benchmark several attacks with and without smoothing under a white-box scenario and evaluate their transferability. Despite the additional constraint of smoothness, our attack has the same probability of success at lower distortion.