A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

• URL: http://arxiv.org/abs/2505.10924v2
• Date: Mon, 26 May 2025 14:15:54 GMT
• Title: A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
• Authors: Ada Chen, Yongjiang Wu, Junyuan Zhang, Jingyu Xiao, Shu Yang, Jen-tse Huang, Kun Wang, Wenxuan Wang, Shuai Wang,
• Abstract summary: We present a systematization of knowledge on the safety and security threats of emphComputer-Using Agents.<n> CUAs are capable of autonomously performing tasks such as navigating desktop applications, web pages, and mobile apps.
• Score: 30.063392019347887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emph{Computer-Using Agents} (CUAs), capable of autonomously performing tasks such as navigating desktop applications, web pages, and mobile apps. However, as these agents grow in capability, they also introduce novel safety and security risks. Vulnerabilities in LLM-driven reasoning, with the added complexity of integrating multiple software components and multimodal inputs, further complicate the security landscape. In this paper, we present a systematization of knowledge on the safety and security threats of CUAs. We conduct a comprehensive literature review and distill our findings along four research objectives: \textit{\textbf{(i)}} define the CUA that suits safety analysis; \textit{\textbf{(ii)} } categorize current safety threats among CUAs; \textit{\textbf{(iii)}} propose a comprehensive taxonomy of existing defensive strategies; \textit{\textbf{(iv)}} summarize prevailing benchmarks, datasets, and evaluation metrics used to assess the safety and performance of CUAs. Building on these insights, our work provides future researchers with a structured foundation for exploring unexplored vulnerabilities and offers practitioners actionable guidance in designing and deploying secure Computer-Using Agents.

Related papers

• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• A Systematization of Security Vulnerabilities in Computer Use Agents [1.3560089220432787]
  We conduct a systematic threat analysis and testing of real-world CUAs under adversarial conditions.<n>We identify seven classes of risks unique to the CUA paradigm, and analyze three concrete exploit scenarios in depth.<n>These case studies reveal deeper architectural flaws across current CUA implementations.
  arXiv  Detail & Related papers  (2025-07-07T19:50:21Z)
• TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems [2.462408812529728]
  This review presents a structured analysis of textbfTrust, Risk, and Security Management (TRiSM) in the context of LLM-based Agentic Multi-Agent Systems (AMAS)<n>We begin by examining the conceptual foundations of Agentic AI and highlight its architectural distinctions from traditional AI agents.<n>We then adapt and extend the AI TRiSM framework for Agentic AI, structured around four key pillars: Explainability, ModelOps, Security, Privacy and Governance.
  arXiv  Detail & Related papers  (2025-06-04T16:26:11Z)
• Securing AI Agents with Information-Flow Control [19.157953827101412]
  This paper explores the use of information-flow control (IFC) to provide security guarantees for AI agents.<n>We present a formal model to reason about the security and expressiveness of agent planners.<n>We present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding information.
  arXiv  Detail & Related papers  (2025-05-29T16:50:41Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• The Hidden Dangers of Browsing AI Agents [0.0]
  This paper presents a comprehensive security evaluation of such agents, focusing on systemic vulnerabilities across multiple architectural layers.<n>Our work outlines the first end-to-end threat model for browsing agents and provides actionable guidance for securing their deployment in real-world environments.
  arXiv  Detail & Related papers  (2025-05-19T13:10:29Z)
• RedTeamLLM: an Agentic AI framework for offensive security [0.0]
  We propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks.<n>RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity.<n> Evaluation is performed through the automated resolution of a range of entry-level, but not trivial, CTF challenges.
  arXiv  Detail & Related papers  (2025-05-11T09:19:10Z)
• From Texts to Shields: Convergence of Large Language Models and Cybersecurity [15.480598518857695]
  This report explores the convergence of large language models (LLMs) and cybersecurity.<n>It examines emerging applications of LLMs in software and network security, 5G vulnerability analysis, and generative security engineering.
  arXiv  Detail & Related papers  (2025-05-01T20:01:07Z)
• A Survey on (M)LLM-Based GUI Agents [62.57899977018417]
  Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction.<n>Recent advances in large language models and multimodal learning have revolutionized GUI automation across desktop, mobile, and web platforms.<n>This survey identifies key technical challenges, including accurate element localization, effective knowledge retrieval, long-horizon planning, and safety-aware execution control.
  arXiv  Detail & Related papers  (2025-03-27T17:58:31Z)
• Security of AI Agents [5.468745160706382]
  We identify and describe potential vulnerabilities in AI agents in detail from a system security perspective.<n>We introduce defense mechanisms corresponding to each vulnerability with design and experiments to evaluate their viability.<n>This paper contextualizes the security issues in the current development of AI agents and delineates methods to make AI agents safer and more reliable.
  arXiv  Detail & Related papers  (2024-06-12T23:16:45Z)
• Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal [0.0]
  We propose a risk assessment process using tools like the risk rating methodology which is used for traditional systems. We conduct scenario analysis to identify potential threat agents and map the dependent system components against vulnerability factors. We also map threats against three key stakeholder groups.
  arXiv  Detail & Related papers  (2024-03-20T05:17:22Z)
• The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective [64.36680481458868]
  Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network's edge. This paper provides a survey of security and privacy in MEC from the perspective of Artificial Intelligence (AI) We focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI.
  arXiv  Detail & Related papers  (2024-01-03T07:47:22Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Towards Automated Classification of Attackers' TTPs by combining NLP with ML Techniques [77.34726150561087]
  We evaluate and compare different Natural Language Processing (NLP) and machine learning techniques used for security information extraction in research. Based on our investigations we propose a data processing pipeline that automatically classifies unstructured text according to attackers' tactics and techniques.
  arXiv  Detail & Related papers  (2022-07-18T09:59:21Z)
• Realistic simulation of users for IT systems in cyber ranges [63.20765930558542]
  We instrument each machine by means of an external agent to generate user activity. This agent combines both deterministic and deep learning based methods to adapt to different environment. We also propose conditional text generation models to facilitate the creation of conversations and documents.
  arXiv  Detail & Related papers  (2021-11-23T10:53:29Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)
• Vulnerabilities of Connectionist AI Applications: Evaluation and Defence [0.0]
  This article deals with the IT security of connectionist artificial intelligence (AI) applications, focusing on threats to integrity. A comprehensive list of threats and possible mitigations is presented by reviewing the state-of-the-art literature. The discussion of mitigations is likewise not restricted to the level of the AI system itself but rather advocates viewing AI systems in the context of their supply chains.
  arXiv  Detail & Related papers  (2020-03-18T12:33:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.