# Adversarial CAPTCHAs

## TL;DR

This paper introduces a framework and system for generating adversarial CAPTCHAs that enhance security against automated attacks while preserving usability, supported by extensive evaluations and open-source resources.

## Contribution

It presents a novel framework and the aCAPTCHA system for creating adversarial CAPTCHAs using advanced image generation techniques, improving security without sacrificing usability.

## Key findings

- Adversarial CAPTCHAs significantly increase security against attacks.
- The aCAPTCHA system maintains usability comparable to normal CAPTCHAs.
- Open-sourced tools facilitate further research in CAPTCHA security.

## Abstract

Following the principle of to set one's own spear against one's own shield, we study how to design adversarial CAPTCHAs in this paper. We first identify the similarity and difference between adversarial CAPTCHA generation and existing hot adversarial example (image) generation research. Then, we propose a framework for text-based and image-based adversarial CAPTCHA generation on top of state-of-the-art adversarial image generation techniques. Finally, we design and implement an adversarial CAPTCHA generation and evaluation system, named aCAPTCHA, which integrates 10 image preprocessing techniques, 9 CAPTCHA attacks, 4 baseline adversarial CAPTCHA generation methods, and 8 new adversarial CAPTCHA generation methods. To examine the performance of aCAPTCHA, extensive security and usability evaluations are conducted. The results demonstrate that the generated adversarial CAPTCHAs can significantly improve the security of normal CAPTCHAs while maintaining similar usability. To facilitate the CAPTCHA security research, we also open source the aCAPTCHA system, including the source code, trained models, datasets, and the usability evaluation interfaces.