Capture the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks

TL;DR

This paper introduces CAPTURE, a novel CAPTCHA scheme leveraging adversarial examples to create challenges that are easy for humans but difficult for machine learning-based bots, enhancing web security.

Contribution

The paper presents a new CAPTCHA design using adversarial examples to improve robustness against ML-powered bot attacks, a novel application of adversarial techniques.

Findings

CAPTURE effectively thwarts ML-based bot solvers.

Humans find CAPTURE CAPTCHAs easy to solve.

CAPTURE maintains user-friendly experience while enhancing security.

Abstract

To this date, CAPTCHAs have served as the first line of defense preventing unauthorized access by (malicious) bots to web-based services, while at the same time maintaining a trouble-free experience for human visitors. However, recent work in the literature has provided evidence of sophisticated bots that make use of advancements in machine learning (ML) to easily bypass existing CAPTCHA-based defenses. In this work, we take the first step to address this problem. We introduce CAPTURE, a novel CAPTCHA scheme based on adversarial examples. While typically adversarial examples are used to lead an ML model astray, with CAPTURE, we attempt to make a "good use" of such mechanisms. Our empirical evaluations show that CAPTURE can produce CAPTCHAs that are easy to solve by humans while at the same time, effectively thwarting ML-based bot solvers.