English
Related papers

Related papers: AgentTrust: Runtime Safety Evaluation and Intercep…

200 papers

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Machine Learning · Computer Science 2025-04-15 Aryan Bhatt , Cody Rushing , Adam Kaufman , Tyler Tracy , Vasil Georgiev , David Matolcsi , Akbir Khan , Buck Shlegeris

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

Artificial Intelligence · Computer Science 2026-02-03 Hanjun Luo , Shenyu Dai , Chiming Ni , Xinfeng Li , Guibin Zhang , Kun Wang , Tongliang Liu , Hanan Salam

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

Software Engineering · Computer Science 2026-01-14 Aarya Doshi , Yining Hong , Congying Xu , Eunsuk Kang , Alexandros Kapravelos , Christian Kästner

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…

Cryptography and Security · Computer Science 2026-03-25 Ali Dehghantanha , Sajad Homayoun

LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…

Computation and Language · Computer Science 2026-05-15 Boxuan Zhang , Jianing Zhu , Zeru Shi , Dongfang Liu , Ruixiang Tang

Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag…

Cryptography and Security · Computer Science 2026-04-29 Lijia Lv , Xuehai Tang , Jie Wen , Jizhong Han , Songlin Hu

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Cryptography and Security · Computer Science 2025-08-22 Zhiqiang Wang , Yichao Gao , Yanting Wang , Suyuan Liu , Haifeng Sun , Haoran Cheng , Guanquan Shi , Haohua Du , Xiangyang Li

As cyber threats continue to evolve in complexity and frequency, robust endpoint protection is essential for organizational security. This paper presents "Endpoint Security Agent: A Comprehensive Approach to Real-time System Monitoring and…

Cryptography and Security · Computer Science 2025-11-12 Srihari R , Ayesha Taranum , Karthik , Mohammed Usman Hussain

The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning, multi-step tool integration, and emergent interactions. It raises some risk factors for…

Multiagent Systems · Computer Science 2025-12-04 Rafflesia Khan , Declan Joyce , Mansura Habiba

As AI agents expand into high-stakes domains like network system operations, evaluating their real-world reliability becomes increasingly critical. However, existing benchmarks risk contamination due to static design, show high statistical…

Networking and Internet Architecture · Computer Science 2026-03-17 Yajie Zhou , Jiajun Ruan , Eric S. Wang , Sadjad Fouladi , Francis Y. Yan , Kevin Hsieh , Zaoxing Liu

We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine…

Machine Learning · Computer Science 2025-07-01 Alex Egg , Martin Iglesias Goyanes , Friso Kingma , Andreu Mora , Leandro von Werra , Thomas Wolf

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We…

Cryptography and Security · Computer Science 2026-03-13 Frank Li

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

Machine Learning · Computer Science 2026-04-07 Ninghui Li , Kaiyuan Zhang , Kyle Polley , Jerry Ma

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

Cryptography and Security · Computer Science 2024-12-19 Yifeng He , Ethan Wang , Yuyang Rong , Zifei Cheng , Hao Chen

As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution…

Machine Learning · Computer Science 2026-03-30 Zhaohui Geoffrey Wang

Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focused on the input and output boundaries, but each task involves…

Cryptography and Security · Computer Science 2026-03-06 Ivoline C. Ngong , Keerthiram Murugesan , Swanand Kadhe , Justin D. Weisz , Amit Dhurandhar , Karthikeyan Natesan Ramamurthy

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

Artificial Intelligence · Computer Science 2026-05-26 Jingwei Sun , Jianing Zhu , Yuanyi Li , Tongliang Liu , Xia HU , Bo Han

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second,…

AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current…

Cryptography and Security · Computer Science 2026-03-24 Uchi Uchibeke

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…

Human-Computer Interaction · Computer Science 2026-02-20 Madeleine Grunde-McLaughlin , Hussein Mozannar , Maya Murad , Jingya Chen , Saleema Amershi , Adam Fourney