English
Related papers

Related papers: QuadSentinel: Sequent Safety for Machine-Checkable…

200 papers

Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where…

Artificial Intelligence · Computer Science 2026-04-07 Zhuowen Yuan , Zhaorun Chen , Zhen Xiang , Nathaniel D. Bastian , Seyyed Hadi Hashemi , Chaowei Xiao , Wenbo Guo , Bo Li

The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however,…

Artificial Intelligence · Computer Science 2025-08-28 Quanfeng Lu , Zhantao Ma , Shuai Zhong , Jin Wang , Dahai Yu , Michael K. Ng , Ping Luo

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Cryptography and Security · Computer Science 2026-05-12 Xixun Lin , Yang Liu , Yancheng Chen , Yongxuan Wu , Yucheng Ning , Yilong Liu , Nan Sun , Shun Zhang , Bin Chong , Chuan Zhou , Yanan Cao

Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains. One example is systems that interact with users, log user actions and behaviour, and make recommendations of items of potential…

Information Retrieval · Computer Science 2021-09-15 Christian Hansen

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

Artificial Intelligence · Computer Science 2026-03-30 Haoyu Wang , Christopher M. Poskitt , Jiali Wei , Jun Sun

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

Artificial Intelligence · Computer Science 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

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

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in…

Cryptography and Security · Computer Science 2026-02-03 Alsharif Abuadbba , Nazatul Sultan , Surya Nepal , Sanjay Jha

Existing methods for safe multi-agent control using logic specifications like Signal Temporal Logic (STL) often face scalability issues. This is because they rely either on single-agent perspectives or on Mixed Integer Linear Programming…

Multiagent Systems · Computer Science 2025-01-13 Joe Eappen , Zikang Xiong , Dipam Patel , Aniket Bera , Suresh Jagannathan

Neural networks (NNs) have been shown to learn complex control laws successfully, often with performance advantages or decreased computational cost compared to alternative methods. Neural network controllers (NNCs) are, however, highly…

Systems and Control · Electrical Eng. & Systems 2023-09-08 Oliver Gates , Matthew Newton , Konstantinos Gatsis

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on…

The rapid advancement of artificial intelligence (AI) has significantly expanded the attack surface for AI-driven cybersecurity threats, necessitating adaptive defense strategies. This paper introduces CyberSentinel, a unified, single-agent…

Cryptography and Security · Computer Science 2025-02-24 Krti Tallam

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Computation and Language · Computer Science 2025-09-29 Yahan Yang , Soham Dan , Shuo Li , Dan Roth , Insup Lee

The development of safety-critical systems requires the control of hazards that can potentially cause harm. To this end, safety engineers rely during the development phase on architectural solutions, called safety patterns, such as safety…

Systems and Control · Electrical Eng. & Systems 2020-09-23 Yuri Gil Dantas , Antoaneta Kondeva , Vivek Nigam

Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt injection, indirect instructions, and visual attacks. Existing defenses typically rely on…

Computation · Statistics 2026-05-14 Kebin Contreras , Carlos Hinojosa , Jorge Bacca , Bernard Ghanem

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

Computation and Language · Computer Science 2026-03-04 Adi Simhi , Jonathan Herzig , Martin Tutek , Itay Itzhak , Idan Szpektor , Yonatan Belinkov

The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…

Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk write operations proceed without independent review, complex tasks lack acceptance…

Artificial Intelligence · Computer Science 2026-05-12 Kai Pan , Rong Hou

Control barrier functions (CBFs) have recently become a powerful method for rendering desired safe sets forward invariant in single- and multi-agent systems. In the multi-agent case, prior literature has considered scenarios where all…

Optimization and Control · Mathematics 2021-02-10 James Usevitch , Dimitra Panagou

As generative AI enters enterprise workflows, ensuring compliance with legal, ethical, and reputational standards becomes a pressing challenge. In beauty tech, where biometric and personal data are central, traditional reviews are often…

Human-Computer Interaction · Computer Science 2025-11-19 Junwei Li , Wenqing Wang , Huiliu Mao , Jiazhe Ni , Zeyu Xiong