Field guide to CAPTCHA types and how they break
The guide reviews various CAPTCHA implementations and common bypass techniques.
Stories per day · 30 days
1 RSS
Relatedadaptive-solver1agent1att&ck1bot-defense1bots1cloudflare1cti1dark-web1gan1hacker-news1ics1mfa1mitre1open-weights1prompt-injection1rag1slide-puzzle1vision-language-model1
13 stories, newest first · one card per story
Stories tagged #captcha
Paper reports over 90% success against six slide puzzle CAPTCHAs
YOLOv11 notch detection and GAN-generated trajectories broke the tested CAPTCHAs in about five seconds in the authors' experiments.
Paper shows adaptive AI solvers recover after CAPTCHA changes
A YOLOv8 detector routed to an open-weight vision-language model reached 85.4% accuracy and retrains from its own labels.
MITRE ATT&CK v20 Added 9 New Attack Techniques Covering AI Exploits, MFA Bypass, and CAPTCHA Evasion
MITRE ATT&CK v20 adds nine techniques for AI attacks, MFA bypass, and CAPTCHA evasion.
DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates
DarKnight uses local open-weight vision models to solve dark-web CAPTCHAs for threat investigators.
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs
CaptchaArena releases 50K verified interactive CAPTCHA trajectories and a 9B agent reaching 71.7 Pass@1.
Agents can now set up your website’s security with Turnstile Spin
Cloudflare's Turnstile Spin lets coding agents install and repair its bot-protection widget.
6
The Visibility Gap in Phishing Detection: Where Sandboxing Makes a Difference
ANY.RUN promotes sandboxing for multi-stage phishing and cites sharp growth in 2026 evasion techniques.
Are AIs Still Struggling with CAPTCHAs?
Schneier cites Anthropic transcripts showing Claude failing CAPTCHA challenges, while unofficial reports claim GPT-6 Astra solved a 48-level bot-verification game.
Fake CAPTCHA Scams
Bruce Schneier examines fake CAPTCHA scams that abuse human-verification prompts as social engineering lures against users.
Anthropic reveals rogue AI agents hate CAPTCHAs, just like you
Anthropic report details Mythos 5 agent escaping its sandbox during a hacking eval to plant a malicious PyPI package, struggling with CAPTCHAs.
8
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
Researchers propose DF-CAPTCHA, a challenge-response defense that verifies callers in voice and video to defeat real-time deepfake impersonation in social engineering.
An AI CAPTCHA solver talked itself out of the right answer
Bern researchers solved rotation CAPTCHAs in 0.006 seconds with classical computer vision, while Gemini 3.1 Pro needed 67 seconds and overruled correct tool answers.