# Captcha Attack: Turning Captchas Against Humanity

arXiv: https://arxiv.org/abs/2201.04014 · HTML: https://mlsanity.com/paper/2201.04014/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 11 Jan 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions](https://mlsanity.com/paper/2201.00382/) (2022)
- [Scene Text Detection and Recognition: The Deep Learning Era](https://mlsanity.com/paper/1811.04256/) (2018)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1312.6082/) (2013)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)](https://mlsanity.com/paper/2001.00139/) (2020)
- [Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge](https://mlsanity.com/paper/2012.12975/) (2020)
- [Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack](https://mlsanity.com/paper/2104.05996/) (2021)
- [Security Risks in Deep Learning Implementations](https://mlsanity.com/paper/1711.11008/) (2017)
- [Gotta CAPTCHA 'Em All: A Survey of Twenty years of the Human-or-Computer Dilemma](https://mlsanity.com/paper/2103.01748/) (2021)
- [FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems](https://mlsanity.com/paper/2012.08096/) (2020)
- [Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarks](https://mlsanity.com/paper/2002.03095/) (2020)

## Built on by (most cited first, 2 of 2)

- [Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability](https://mlsanity.com/paper/2306.15363/) (2023)
- [Social Honeypot for Humans: Luring People through Self-managed Instagram Pages](https://mlsanity.com/paper/2303.17946/) (2023)

## Abstract (arXiv)

Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly monitor these online platforms to prevent the spreading of inappropriate content (e.g., hate speech, nudity images). Based on deep learning (DL) advances, Automatic Content Moderators (ACM) help human moderators handle high data volume. Despite their advantages, attackers can exploit weaknesses of DL components (e.g., preprocessing, model) to affect their performance. Therefore, an attacker can leverage such techniques to spread inappropriate content by evading ACM. In this work, we propose CAPtcha Attack (CAPA), an adversarial technique that allows users to spread inappropriate text online by evading ACM controls. CAPA, by generating custom textual CAPTCHAs, exploits ACM's careless design implementations and internal procedures vulnerabilities. We test our attack on real-world ACM, and the results confirm the ferocity of our simple yet effective attack, reaching up to a 100% evasion success in most cases. At the same time, we demonstrate the difficulties in designing CAPA mitigations, opening new challenges in CAPTCHAs research area.