English
Related papers

Related papers: Towards Verifiably Safe Tool Use for LLM Agents

200 papers

Agentic systems powered by large language models (LLMs) are becoming progressively more complex and capable. Their increasing agency and expanding deployment settings attract growing attention to effective governance policies, monitoring,…

Computers and Society · Computer Science 2025-08-06 Garry A. Gabison , R. Patrick Xian

A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs). These attacks may extract private information or coerce the model into producing harmful outputs. In real-world deployments,…

Machine Learning · Computer Science 2025-02-13 Ang Li , Yin Zhou , Vethavikashini Chithrra Raghuram , Tom Goldstein , Micah Goldblum

The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks and labor-intensive data collection, limiting practical…

Artificial Intelligence · Computer Science 2025-08-05 Zhiwei Liu , Jielin Qiu , Shiyu Wang , Jianguo Zhang , Zuxin Liu , Roshan Ram , Haolin Chen , Weiran Yao , Shelby Heinecke , Silvio Savarese , Huan Wang , Caiming Xiong

Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and…

Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…

Cryptography and Security · Computer Science 2025-09-01 Georgios Syros , Anshuman Suri , Jacob Ginesin , Cristina Nita-Rotaru , Alina Oprea

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces…

Cryptography and Security · Computer Science 2026-03-25 Charoes Huang , Xin Huang , Ngoc Phu Tran , Amin Milani Fard

In many safety-critical engineering domains, hazard analysis techniques are an essential part of requirement elicitation. Of the methods proposed for this task, STPA (System-Theoretic Process Analysis) represents a relatively recent…

Software Engineering · Computer Science 2025-03-18 Ali Raeisdanaei , Juho Kim , Michael Liao , Sparsh Kochhar

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for…

Computation and Language · Computer Science 2025-09-30 Huihao Jing , Haoran Li , Wenbin Hu , Qi Hu , Heli Xu , Tianshu Chu , Peizhao Hu , Yangqiu Song

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

Software Engineering · Computer Science 2026-03-20 Xuan Chen , Lu Yan , Ruqi Zhang , Xiangyu Zhang

The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by…

Software Engineering · Computer Science 2025-10-08 Lesly Miculicich , Mihir Parmar , Hamid Palangi , Krishnamurthy Dj Dvijotham , Mirko Montanari , Tomas Pfister , Long T. Le

The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces…

Cryptography and Security · Computer Science 2026-03-12 Nanzi Yang , Weiheng Bai , Kangjie Lu

Large Language Models (LLMs) are transforming artificial intelligence, enabling autonomous agents to perform diverse tasks across various domains. These agents, proficient in human-like text comprehension and generation, have the potential…

Artificial Intelligence · Computer Science 2024-04-10 Saikat Barua

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…

Cryptography and Security · Computer Science 2025-08-22 Hengyu An , Jinghuai Zhang , Tianyu Du , Chunyi Zhou , Qingming Li , Tao Lin , Shouling Ji

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually…

Cryptography and Security · Computer Science 2026-04-29 Even Eilertsen , Vasileios Mavroeidis , Gudmund Grov

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Cryptography and Security · Computer Science 2024-07-31 Boyang Zhang , Yicong Tan , Yun Shen , Ahmed Salem , Michael Backes , Savvas Zannettou , Yang Zhang

The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based…

Cryptography and Security · Computer Science 2026-03-10 Yuhang Huang , Boyang Ma , Biwei Yan , Xuelong Dai , Yechao Zhang , Minghui Xu , Kaidi Xu , Yue Zhang

Large Language Models (LLMs) are increasingly used to build autonomous agents that perform complex tasks with external tools, often exposed through APIs in enterprise systems. Direct use of these APIs is difficult due to the complex input…

Trust in AI agents has been extensively studied in the literature, resulting in significant advancements in our understanding of this field. However, the rapid advancements in Large Language Models (LLMs) and the emergence of LLM-based AI…

Artificial Intelligence · Computer Science 2023-08-11 Sivan Schwartz , Avi Yaeli , Segev Shlomov

Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access,…

Cryptography and Security · Computer Science 2026-05-14 Jehyeok Yeon , Isha Chaudhary , Gagandeep Singh