# Attack Type Agnostic Perceptual Enhancement of Adversarial Images

arXiv: https://arxiv.org/abs/1903.03029 · HTML: https://mlsanity.com/paper/1903.03029/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2019.

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

- [Imperceptible Adversarial Examples by Spatial Chroma-Shift](https://mlsanity.com/paper/2108.02502/) (2021)
- [A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications](https://mlsanity.com/paper/2304.10679/) (2023)
- [Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces](https://mlsanity.com/paper/2310.13950/) (2023)

## Abstract (arXiv)

Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced during the adversarial image generation process degrades the perceptual quality and introduces artificial colours; making it also difficult for humans to classify images and recognise objects. In this letter, we propose a method to enhance the perceptual quality of these adversarial images. The proposed method is attack type agnostic and could be used in association with the existing attacks in the literature. Our experiments show that the generated adversarial images have lower Euclidean distance values while maintaining the same adversarial attack performance. Distances are reduced by 5.88% to 41.27% with an average reduction of 22% over the different attack and network types.