'Out of Sight': CAPE Poisons Web Content So Agentic Crawlers Lose Up to 75.8% More Information

arXiv·medium signal

CAPE injects human-imperceptible perturbations that survive into agent compressors and cause large information loss when text is processed by AI crawlers, extracting disruptive patterns from accessible compressors and adapting them to targets via evolutionary optimization. It reports up to 75.8% higher information loss than the strongest baseline while preserving visual fidelity, with demonstrated transfer to LangGraph agent workflows and GitHub Copilot. A content-protection angle for publishers reacting to agentic scraping.