English
Related papers

Related papers: Governed MCP: Kernel-Level Tool Governance for AI …

200 papers

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful…

Cryptography and Security · Computer Science 2025-08-28 David Noever

Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce…

Artificial Intelligence · Computer Science 2026-03-25 Alfred Shen , Aaron Shen

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…

Cryptography and Security · Computer Science 2026-04-24 Ari Azarafrooz

The Model Context Protocol (MCP) enables large language models (LLMs) to access external resources on demand. While commonly assumed to enhance performance, how LLMs actually leverage this capability remains poorly understood. We introduce…

Artificial Intelligence · Computer Science 2025-08-19 Wei Song , Haonan Zhong , Ziqi Ding , Jingling Xue , Yuekang Li

Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…

Artificial Intelligence · Computer Science 2026-01-26 Zhibo Liang , Tianze Hu , Zaiye Chen , Mingjie Tang

Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level approach to AI alignment that reframes alignment from…

The Model Context Protocol (MCP) has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensibility and rich integrations, it also introduces a…

Cryptography and Security · Computer Science 2025-07-10 Zhihao Li , Kun Li , Boyang Ma , Minghui Xu , Yue Zhang , Xiuzhen Cheng

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GUI agents, whose evaluation methods are susceptible to UI…

Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…

Cryptography and Security · Computer Science 2025-11-19 Katsuaki Nakano , Reza Fayyazi , Shanchieh Jay Yang , Michael Zuzak

AI agents increasingly run untrusted code on developer machines: shell commands generated by language models, third-party scripts retrieved at runtime, and tool plugins of unknown provenance. Existing isolation mechanisms impose tradeoffs…

Cryptography and Security · Computer Science 2026-05-27 Cong Wang , Yusheng Zheng

AI agents, autonomous digital actors, need agent-native protocols; existing methods include GUI automation and MCP-based skills, with defects of high token consumption, fragmented interaction, inadequate security, due to lacking a unified…

Artificial Intelligence · Computer Science 2026-04-07 Xu Mingze

Multi-agent systems (MAS) powered by artificial intelligence (AI) are increasingly foundational to complex, distributed workflows. Yet, the security of their underlying communication protocols remains critically under-examined. This paper…

Cryptography and Security · Computer Science 2025-11-07 Yedidel Louck , Ariel Stulman , Amit Dvir

Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that…

Artificial Intelligence · Computer Science 2026-03-20 Vedanta S P , Ponnurangam Kumaraguru

The Transmission Control Protocol (TCP) relies on a state machine and deterministic arithmetic to ensure reliable connections. However, traditional protocol logic driven by hard-coded state machines struggles to meet the demands of…

Networking and Internet Architecture · Computer Science 2025-12-02 Yule Han , Kezhi Wang , Kun Yang

Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-10 Shiva Sai Krishna Anand Tokal , Vaibhav Jha , Anand Eswaran , Praveen Jayachandran , Yogesh Simmhan

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Artificial Intelligence · Computer Science 2026-02-18 Sanidhya Vijayvargiya , Aditya Bharat Soni , Xuhui Zhou , Zora Zhiruo Wang , Nouha Dziri , Graham Neubig , Maarten Sap

The deployment of Large Language Model (LLM)-generated SQL queries in Artificial Intelligence of Things (AIoT) systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries…

Cryptography and Security · Computer Science 2026-05-08 Wonbae Kim , Hee-Kyong Yoo

Agentic AI systems - capable of goal interpretation, world modeling, planning, tool use, long-horizon operation, and autonomous coordination - introduce distinct control failures not addressed by existing safety frameworks. We identify six…

Computers and Society · Computer Science 2026-03-05 Subramanyam Sahoo

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

Software Engineering · Computer Science 2025-12-29 Brian Bowers , Smita Khapre , Jugal Kalita