Captcha Attack: Turning Captchas Against Humanity

01/11/2022
by   Mauro Conti, et al.
6

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 same time, we demonstrate the difficulties in designing CAPA mitigations, opening new challenges in CAPTCHAs research area.

READ FULL TEXT

page 2

page 7

page 8

research
09/14/2023

Disinformation Echo-chambers on Facebook

The landscape of information has experienced significant transformations...
research
08/18/2023

An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software

The exponential growth of social media platforms has brought about a rev...
research
05/03/2021

Towards A Multi-agent System for Online Hate Speech Detection

This paper envisions a multi-agent system for detecting the presence of ...
research
09/12/2022

A Review of Challenges in Machine Learning based Automated Hate Speech Detection

The spread of hate speech on social media space is currently a serious i...
research
09/13/2022

PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models

Deep Learning (DL) models increasingly power a diversity of applications...
research
09/28/2017

A Web of Hate: Tackling Hateful Speech in Online Social Spaces

Online social platforms are beset with hateful speech - content that exp...
research
01/19/2020

An Approach for Time-aware Domain-based Social Influence Prediction

Online Social Networks(OSNs) have established virtual platforms enabling...

Please sign up or login with your details

Forgot password? Click here to reset