Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability

• URL: http://arxiv.org/abs/2605.07110v1
• Date: Fri, 08 May 2026 01:38:46 GMT
• Title: Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
• Abstract summary: The article develops an architecture-lifecycle framework for deployment-grounded reliability in CUAs.<n>The analysis synthesizes representative systems,benchmarks, and security/privacy studies.
• Score: 21.333731425525205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and tool backends. In such settings, reliability isno longer captured by task success alone: perception errors,planning drift, memory use, tool mediation, permission scope,and runtime oversight jointly determine whether agent actionsremain aligned with user intent, Existing surveys organize theCUA landscape by methods, platforms, benchmarks, or securitythreats, but less explicitly connect capability formation, author-ity exposure, failure manifestation, and control placement. Toaddress this gap, the article develops an architecture-lifecycleframework for deployment-grounded reliability in CUAs. Thearchitectural view analyzes Perception, Decision, and Executionas coupled layers that transform software observations intoauthority-bearing actions, The lifecycle view examines Creation.Deployment, Operation, and Maintenance as stages in which priorsare learned, tools and permissions are bound, runtime trajecto.ries are stressed, and assurance must be preserved under drift.Using this lens, the analysis synthesizes representative systems,benchmarks, and security/privacy studies; distinguishes wherefailures become visible from where their enabling conditions areintroduced, and maps recurring intervention surfaces for controloversight, and assurance. OpenClaw is used only as a public moti.vating example of an open deployment pattern, not as a verifedinternal case study. The conclusion highlights open challengesin controllable grounding, long-horizon constraint preservation,safe authority binding, mixed-trust runtime defense, privacy-preserving memory,and continual assurance.

Related papers

• Forward-Deployed Full-Stack Engineering for Autonomous Cloud MLOps [0.0]
  We present an evidence-gated multi-agent framework for transforming a natural-language MLOps cloud engineering task into a verified repository and operational cloud deployment.<n>We realize the framework on Google Cloud Platform and evaluate repository completeness, controlled execution, evidence-gated transitions, cloud promotion, and bounded recovery.
  arXiv  Detail & Related papers  (2026-08-30T07:13:10Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Open Security Benchmark: Towards Autonomous Enterprise Cyber Defense [0.49157446832511503]
  We present Open Security Benchmark (OSB), a framework that agentic AI on this work.<n>OSB surfaces a curated enterprise environment - a frozen, holistic view of the security state.<n>OSB is built from five components: a data layer, a task and evaluation-set layer, a multi-dimensional scoring layer, a minimal auditable harness.
  arXiv  Detail & Related papers  (2026-07-29T14:46:04Z)
• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels [53.63220028820581]
  Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.<n>We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably.
  arXiv  Detail & Related papers  (2026-07-28T17:50:44Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• Clawed and Dangerous: Can We Trust Open Agentic Systems? [12.04979073308511]
  Open agentic systems combine planning with external capabilities, persistent memory, and privileged execution.<n>This paper introduces a six-dimensional analytical taxonomy and synthesizes 50 papers spanning attacks, benchmarks, defenses, audits, and adjacent engineering foundations.<n>Our review shows that the literature is relatively mature in attack characterization and benchmark construction, but remains weak in deployment controls, operational governance, persistent-memory integrity, and capability revocation.
  arXiv  Detail & Related papers  (2026-03-27T09:45:12Z)
• A Trace-Based Assurance Framework for Agentic AI Orchestration: Contracts, Testing, and Governance [0.22940141855172028]
  This paper presents an assurance framework for Agentic AI systems using Large Language Models (LLMs)<n>Executions are instrumented as Message-Action Traces (MAT) with explicit step and trace contracts.<n>The framework includes stress testing, formulated as a budgeted counterexample search over bounded perturbations.
  arXiv  Detail & Related papers  (2026-03-18T10:23:48Z)
• Detecting Object Tracking Failure via Sequential Hypothesis Testing [80.7891291021747]
  Real-time online object tracking in videos constitutes a core task in computer vision.<n>We propose interpreting object tracking as a sequential hypothesis test, wherein evidence for or against tracking failures is gradually accumulated over time.<n>We propose both supervised and unsupervised variants by leveraging either ground-truth or solely internal tracking information.
  arXiv  Detail & Related papers  (2026-02-13T14:57:15Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Architectures for Building Agentic AI [0.0]
  This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property.<n>Building on classical foundations, we propose a practical taxonomy-tool-using agents, memory-augmented agents, planning and self-improvement agents, multi-agent systems, and embodied or web agents.
  arXiv  Detail & Related papers  (2025-12-10T09:28:40Z)
• SoK: Measuring What Matters for Closed-Loop Security Agents [0.0]
  We introduce CLASP: the Closed-Loop Autonomous Security Performance framework.<n>It aligns the security lifecycle (reconnaissance, exploitation, root cause synthesis analysis, patch synthesis, validation) with core agentic capabilities.<n>We then define the Closed-Loop Capability (CLC) Score, a composite metric quantifying both degree of loop closure and operational effectiveness.
  arXiv  Detail & Related papers  (2025-10-02T04:20:35Z)
• Bridging the Mobile Trust Gap: A Zero Trust Framework for Consumer-Facing Applications [51.56484100374058]
  This paper proposes an extended Zero Trust model designed for mobile applications operating in untrusted, user-controlled environments.<n>Using a design science methodology, the study introduced a six-pillar framework that supports runtime enforcement of trust.<n>The proposed model offers a practical and standards-aligned approach to securing mobile applications beyond pre-deployment controls.
  arXiv  Detail & Related papers  (2025-08-20T18:42:36Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)

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.