English
Related papers

Related papers: StepShield: When, Not Whether to Intervene on Rogu…

200 papers

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

Cryptography and Security · Computer Science 2026-02-25 Julia Bazinska , Max Mathys , Francesco Casucci , Mateo Rojas-Carulla , Xander Davies , Alexandra Souly , Niklas Pfister

AI agents are expected to perform professional work across hundreds of occupational domains (from emergency department triage to nuclear reactor safety monitoring to customs import processing), yet existing benchmarks can only evaluate…

Computation and Language · Computer Science 2026-04-17 Xiaomeng Hu , Yinger Zhang , Fei Huang , Jianhong Tu , Yang Su , Lianghao Deng , Yuxuan Liu , Yantao Liu , Dayiheng Liu , Tsung-Yi Ho

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as…

Artificial Intelligence · Computer Science 2026-05-26 Haiyang Shen , Xuanzhong Chen , Wendong Xu , Yun Ma , Liang Chen , Kuan Li

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

Artificial Intelligence · Computer Science 2026-03-17 Florin Adrian Chitan

Intent-Based Networking (IBN) simplifies network management, but its reliability is challenged by "intent drift", where the network's state gradually deviates from its intended goal, often leading to silent failures. Conventional approaches…

Networking and Internet Architecture · Computer Science 2026-02-17 Md. Kamrul Hossain , Walid Aljoby

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

Computers and Society · Computer Science 2026-02-24 Nelu D. Radpour

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges…

Artificial Intelligence · Computer Science 2026-05-19 Chenning Li , Pan Hu , Justin Xu , Baris Ozbas , Olivia Liu , Caroline Van , Manxue Li , Wei Zhou , Mohammad Alizadeh , Pengyu Zhang , KK Sriramadhesikan , Ming Zhang

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

Artificial Intelligence · Computer Science 2025-06-17 Jingyu Peng , Maolin Wang , Xiangyu Zhao , Kai Zhang , Wanyu Wang , Pengyue Jia , Qidong Liu , Ruocheng Guo , Qi Liu

Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experiences. However, existing methods predominantly inject experience…

Computation and Language · Computer Science 2026-04-16 Wenyuan Zhang , Xinghua Zhang , Haiyang Yu , Shuaiyi Nie , Bingli Wu , Juwei Yue , Tingwen Liu , Yongbin Li

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

As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic interaction with users. However, existing benchmarks fail to…

Artificial Intelligence · Computer Science 2026-05-28 Yunqi Liu , Tong Niu , Zitong Wang , Zhenlong Dai , Yuqi Qing , Weiqiang Wang , Jian Liu

Reinforcement learning (RL) is increasingly used to personalize instruction in intelligent tutoring systems, yet the field lacks a formal framework for defining and evaluating pedagogical safety. We introduce a four-layer model of…

Artificial Intelligence · Computer Science 2026-04-07 Oluseyi Olukola , Nick Rahimi

Academic integrity continues to face the persistent challenge of examination cheating. Traditional invigilation relies on human observation, which is inefficient, costly, and prone to errors at scale. Although some existing AI-powered…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Van-Truong Le , Le-Khanh Nguyen , Trong-Doanh Nguyen

Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion…

Cryptography and Security · Computer Science 2026-05-22 Danyu Sun , Jinghuai Zhang , Yuan Tian , Zhou Li

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for…

Artificial Intelligence · Computer Science 2025-07-22 Boyuan Zheng , Zeyi Liao , Scott Salisbury , Zeyuan Liu , Michael Lin , Qinyuan Zheng , Zifan Wang , Xiang Deng , Dawn Song , Huan Sun , Yu Su

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…

Cryptography and Security · Computer Science 2025-09-25 Aaron Xuxiang Tian , Ruofan Zhang , Janet Tang , Ji Wang , Tianyu Shi , Jiaxin Wen

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Computation and Language · Computer Science 2025-03-25 Xunguang Wang , Wenxuan Wang , Zhenlan Ji , Zongjie Li , Pingchuan Ma , Daoyuan Wu , Shuai Wang

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users'…

Computation and Language · Computer Science 2025-10-21 Youliang Yuan , Wenxiang Jiao , Yuejin Xie , Chihao Shen , Menghan Tian , Wenxuan Wang , Jen-tse Huang , Pinjia He

LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and malicious instructions, that compromise their execution…

Cryptography and Security · Computer Science 2025-10-14 Jiahao Liu , Bonan Ruan , Xianglin Yang , Zhiwei Lin , Yan Liu , Yang Wang , Tao Wei , Zhenkai Liang