English
Related papers

Related papers: The Authorization-Execution Gap Is a Major Safety …

200 papers

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

Cryptography and Security · Computer Science 2026-02-10 Sai Puppala , Ismail Hossain , Md Jahangir Alam , Yoonpyo Lee , Jay Yoo , Tanzim Ahad , Syed Bahauddin Alam , Sajedul Talukder

Autonomous vehicles (AV) depend on the sensors like RADAR and camera for the perception of the environment, path planning, and control. With the increasing autonomy and interactions with the complex environment, there have been growing…

Systems and Control · Computer Science 2021-06-22 Abu Hasnat Mohammad Rubaiyat , Yongming Qin , Homa Alemzadeh

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…

Software Engineering · Computer Science 2026-04-13 Xiaowen Zhang , Hannuo Zhang , Shin Hwei Tan

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

Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…

Artificial Intelligence · Computer Science 2026-04-21 Hengle Jiang , Ke Tang

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit…

Cryptography and Security · Computer Science 2026-05-20 Kaixiang Wang , Jiong Lou , Zhaojiacheng Zhou , Jie Li

When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environment due to privacy or…

Artificial Intelligence · Computer Science 2026-04-02 Yi Nian , Haosen Cao , Shenzhe Zhu , Henry Peng Zou , Qingqing Luan , Yue Zhao

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

Modern artificial intelligence (AI) systems act with a high degree of independence yet lack legal personhood-a paradox that fractures doctrines grounded in human-centric notions of mens rea and actus reus. This Article introduces…

Computers and Society · Computer Science 2026-03-09 Anirban Mukherjee , Hannah Hanwen Chang

Security policy enforcement in contemporary agentic systems predominantly consists of embedding natural-language policies within an agent's system prompt and delegating compliance to the agent's reasoning. This approach admits no formal…

Cryptography and Security · Computer Science 2026-05-12 Nils Palumbo , Sarthak Choudhary , Jihye Choi , Guy Amir , Prasad Chalasani , Somesh Jha

Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual…

Multiagent Systems · Computer Science 2026-04-28 Ben Hagag , William L. Anderson , Christian Schroeder de Witt , Sarah Scheffler

Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional…

Artificial Intelligence · Computer Science 2026-03-02 Xuyan Ma , Xiaofei Xie , Yawen Wang , Junjie Wang , Boyu Wu , Mingyang Li , Qing Wang

Retrieval-Augmented Generation (RAG) and agentic AI systems are increasingly prevalent in enterprise AI deployments. However, real enterprise environments introduce challenges largely absent from academic treatments and consumer-facing…

Cryptography and Security · Computer Science 2026-05-08 Francisco Javier Arceo , Varsha Prasad Narsing

Separation of the sources and analysis of their connectivity have been an important topic in EEG/MEG analysis. To solve this problem in an automatic manner, we propose a two-layer model, in which the sources are conditionally uncorrelated…

Machine Learning · Computer Science 2012-03-19 Kun Zhang , Aapo Hyvarinen

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

Cryptography and Security · Computer Science 2026-05-18 Zheng Yan , Jingxiang Weng , Charles Chen , Dengyun Peng , Ethan Qin , Jiannan Guan , Jinhao Liu , Qiming Yu , Yixin Yuan , Fanqing Meng , Carl Che , Mengkang Hu

The governance of open-weight artificial intelligence (AI) models has been framed as a binary choice: openness as risk, restriction as safety. This paper challenges that framing, arguing that access restrictions, without governed…

Computers and Society · Computer Science 2026-04-21 Vinicius Santana Gomes

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This position paper argues that personal-agent architecture must move to the edge because the…

Machine Learning · Computer Science 2026-05-19 Chunlin Tian , Dongqi Cai , Wanru Zhao , Nicholas D. Lane

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

Cryptography and Security · Computer Science 2026-05-08 Hao Li , Ruoyao Wen , Shanghao Shi , Ning Zhang , Yevgeniy Vorobeychik , Chaowei Xiao