CAPTCHA Solving

Follow this topic Ask about this topic

Latest papers

8 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates
Oct 14, 2026Binghui Wu, Yeo Zi Yi, Darren Tan +3CAPTCHA Solving Agentic AI
National University of Singapore Singapore · A*STAR Institute of Advanced Intelligence and Compute Singapore
CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving
Oct 9, 2026Shangquan Sun, Ruoyu Chen, Zhirui Liu +4CAPTCHA Solving Tool-Using Vision-Language Agents
Nanyang Technological University, Singapore. · the School of Cyber Security, University of Chinese Academy of Sciences, China. · the School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, Guangdong 518107, P.R. China. +2
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs
Sep 25, 2026Zhenhao Zhang, Zhaoyu Fan, Haohan Ying +5CAPTCHA Solving Computer-Use Agents
Columbia University · Zhejiang University · University of Rochester +1
Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents
Sep 23, 2026Zeyu Zhang, Dingyi Rong, Zijian Chen +3CAPTCHA Solving GUI Agents
Shanghai Jiao Tong University Shanghai, China · Shanghai Artificial Intelligence Laboratory Shanghai, China
Breaking Darknet CAPTCHAs with general purpose LLM
Aug 28, 2026Benjamin Fehrensen, Jens HublerCAPTCHA Solving Large Vision-Language Models
Bern University of Applied Science (BFH)
HLL: Can Agents Cross Humanity's Last Line of Verification?
Jun 1, 2026Xinhao Song, Su Su, Sirui Song +6CAPTCHA Solving GUI Agents
1Shanghai Jiao Tong University · 2Shandong University · 3Tongji University
CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
May 19, 2026Pengcheng Wang, Haoxiang Liu, Yang Dai +5CAPTCHA Solving Visual Reasoning
1Alibaba Group · 2Southern University of Science and Technology · 3Harbin Institute of Technology (Shenzhen)
CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
Mar 23, 2026Yuxi Chen, Haoyu Zhai, Chenkai Wang +4CAPTCHA Solving Synthetic Data Generation
University of Illinois Urbana-Champaign.

Oct 14, 2026J/K move · Enter open · S save

DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates

Binghui Wu, Yeo Zi Yi, Darren Tan, Manit Baser+2

National University of Singapore Singapore · A*STAR Institute of Advanced Intelligence and Compute Singapore

CAPTCHA Solving Agentic AI Cyber Threat Intelligence Retrieval-Augmented Generation

Open paper AskPDF arXiv

Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTCHAs that operators deploy to block automated collection. Existing solvers either need unscalable per-site fine-tuning or rely on commercial Vision-Language Model (VLM) APIs, which surrender operational sovereignty: provider policies, Tor-exit blocking, government regulation, or model updates outside the investigator's control can halt or alter the solver overnight, and per-call costs recur with every session and retry. We present DarKnight, a self-improving agentic framework designed to run on a single workstation GPU inside an investigator's Tor crawler and solve CAPTCHAs with small, locally hosted open-weight VLMs that no provider decision can withdraw, without per-market training or third-party services. For each CAPTCHA, DarKnight retrieves successful and failed past attempts on similar images (dual-signal RAG), composes an image-specific preprocessing pipeline, and learns from the site's pass/fail verdict. In a case study on four real-world dark web marketplaces, agentic tool selection outperformed parameter scaling. A deployable open-weight VLM with DarKnight reached 83.2% on the most heavily defended market, 37.2 percentage points above its base model, outperforming even the frontier Claude Opus~5 (44%). DarKnight recovered 48.2% of baseline failures at a 7.6% degeneration cost, indicating that selective tool use can avoid much of the degradation caused by uniform preprocessing.