Multimodal LLMs reliably solve many CAPTCHA tasks but can be defended by adding fine-grained localization and implicit counting that drops state-of-the-art success from over 95% to 0%.
Open captchaworld: A comprehensive web-based platform for testing and benchmarking multimodal llm agents
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2025 2roles
dataset 1polarities
use dataset 1representative citing papers
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
Multimodal LLMs reliably solve many CAPTCHA tasks but can be defended by adding fine-grained localization and implicit counting that drops state-of-the-art success from over 95% to 0%.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.