English
Related papers

Related papers: SkillSafetyBench: Evaluating Agent Safety under Sk…

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

Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries,…

Software Engineering · Computer Science 2026-05-26 Ting Liu

Large language models (LLMs) are evolving into agentic systems that reason, plan, and operate external tools. The Model Context Protocol (MCP) is a key enabler of this transition, offering a standardized interface for connecting LLMs with…

Computation and Language · Computer Science 2026-03-06 Xuanjun Zong , Zhiqi Shen , Lei Wang , Yunshi Lan , Chao Yang

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Machine Learning · Computer Science 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv

Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination failure and conflict…

Artificial Intelligence · Computer Science 2026-05-25 Pepijn Cobben , Xuanqiang Angelo Huang , Thao Amelia Pham , Isabel Dahlgren , Terry Jingchen Zhang , Zhijing Jin

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…

Cryptography and Security · Computer Science 2026-04-20 Xuwei Ding , Skylar Zhai , Linxin Song , Jiate Li , Taiwei Shi , Nicholas Meade , Siva Reddy , Jian Kang , Jieyu Zhao

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…

Artificial Intelligence · Computer Science 2026-04-07 Prince Zizhuang Wang , Shuli Jiang

As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when prevention fails. We formalize a solution to this neglected…

Artificial Intelligence · Computer Science 2026-05-29 Christy Li , Sky CH-Wang , Andi Peng , Andreea Bobu

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present…

Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Raiyaan Abdullah , Yogesh Singh Rawat , Shruti Vyas

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Artificial Intelligence · Computer Science 2026-05-07 Chenglin Yang

Security incident analysis (SIA) poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex toolchains, and limited analyst expertise. These difficulties…

Cryptography and Security · Computer Science 2026-03-09 Sourov Jajodia , Madeena Sultana , Suryadipta Majumdar , Adrian Taylor , Grant Vandenberghe

Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the…

Computation and Language · Computer Science 2024-08-29 Wei Wang , Dan Zhang , Tao Feng , Boyan Wang , Jie Tang

Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language models (LLMs) and vision language models (VLMs) now assist in…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…

Artificial Intelligence · Computer Science 2026-03-25 Raj Ghugare , Roger Creus Castanyer , Catherine Ji , Kathryn Wantlin , Jin Schofield , Karthik Narasimhan , Benjamin Eysenbach

The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…

Cryptography and Security · Computer Science 2025-10-21 Zonghao Ying , Le Wang , Yisong Xiao , Jiakai Wang , Yuqing Ma , Jinyang Guo , Zhenfei Yin , Mingchuan Zhang , Aishan Liu , Xianglong Liu

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as…

Cryptography and Security · Computer Science 2026-05-15 Seunghyun Lee , David Brumley

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Cryptography and Security · Computer Science 2025-09-10 Haitao Hu , Peng Chen , Yanpeng Zhao , Yuqi Chen
‹ Prev 1 3 4 5 6 7 10 Next ›