HLL is a new benchmark that evaluates eight frontier multimodal agents on closed-loop interactive CAPTCHA solving, showing sharp performance drops under realism stressors and trace validation.
Deep-captcha: a deep learning based captcha solver for vulnerability assessment.arXiv preprint arXiv:2006.08296, 2020
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multi-layer fingerprinting distinguishes LLM web agents from humans and each other while some agents bypass tested anti-bot mechanisms.
citing papers explorer
-
HLL: Can Agents Cross Humanity's Last Line of Verification?
HLL is a new benchmark that evaluates eight frontier multimodal agents on closed-loop interactive CAPTCHA solving, showing sharp performance drops under realism stressors and trace validation.
-
On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer Fingerprinting
Multi-layer fingerprinting distinguishes LLM web agents from humans and each other while some agents bypass tested anti-bot mechanisms.