This page shows the most relevant public items for cs.CR, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Feb 25, 2026 • arXiv • Bo Li, Dan Hendrycks, Julian Thorne
As LLM agents are granted access to execute code, query databases, and interact with file systems, the risk of catastrophic failure or malicious exploit grows exponentially. We propose 'Agency Sand...
Paper • Feb 24, 2026 • arXiv • Sarah Chen, David Wagner, Dawn Song
As autonomous agents increasingly communicate via unstructured natural language, they become vulnerable to 'Intent Redirection'—a novel class of adversarial attacks where a malicious agent hijacks ...
Paper • Feb 20, 2026 • arXiv • J. L. Martinez, Sarah Chen, Arjun Nair
To counter the rise of Agent Hijacking, we propose a framework for 'Verifiable Intent.' This protocol cryptographically anchors the human user's original objective to every sub-task generated by a ...
Paper • Feb 18, 2026 • arXiv • Siddharth V., Elena K., Marcus W., Yujin H.
As agents increasingly handle high-stakes tasks like financial transactions and system permissions, the mechanism of 'Authority Transfer' becomes a critical attack surface. We introduce the Agent-i...