A Systematization of Security Vulnerabilities in Computer Use Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | Jones, Daniel, Severi, Giorgio, Pouliot, Martin, Lopez, Gary, de Gruyter, Joris, Zanella-Beguelin, Santiago, Song, Justin, Bullwinkel, Blake, Cortez, Pamela, Minnich, Amanda |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
por: Bullwinkel, Blake, et al.
Publicado: (2025)
por: Bullwinkel, Blake, et al.
Publicado: (2025)
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
por: Bullwinkel, Blake, et al.
Publicado: (2026)
por: Bullwinkel, Blake, et al.
Publicado: (2026)
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System
por: Munoz, Gary D. Lopez, et al.
Publicado: (2024)
por: Munoz, Gary D. Lopez, et al.
Publicado: (2024)
Securing AI Agents with Information-Flow Control
por: Costa, Manuel, et al.
Publicado: (2025)
por: Costa, Manuel, et al.
Publicado: (2025)
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
por: Pradhan, Gauri, et al.
Publicado: (2025)
por: Pradhan, Gauri, et al.
Publicado: (2025)
Optimizing Agent Planning for Security and Autonomy
por: Kolluri, Aashish, et al.
Publicado: (2026)
por: Kolluri, Aashish, et al.
Publicado: (2026)
Closed-Form Bounds for DP-SGD against Record-level Inference
por: Cherubin, Giovanni, et al.
Publicado: (2024)
por: Cherubin, Giovanni, et al.
Publicado: (2024)
The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
por: Meeus, Matthieu, et al.
Publicado: (2025)
por: Meeus, Matthieu, et al.
Publicado: (2025)
An Analysis of Modern Web Security Vulnerabilities Inside WebAssembly Applications
por: Corrias, Lorenzo, et al.
Publicado: (2026)
por: Corrias, Lorenzo, et al.
Publicado: (2026)
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
por: Hu, Haitao, et al.
Publicado: (2025)
por: Hu, Haitao, et al.
Publicado: (2025)
HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
por: Ren, Xiaoxue, et al.
Publicado: (2025)
por: Ren, Xiaoxue, et al.
Publicado: (2025)
Excavating Vulnerabilities Lurking in Multi-Factor Authentication Protocols: A Systematic Security Analysis
por: Wee, Ang Kok, et al.
Publicado: (2024)
por: Wee, Ang Kok, et al.
Publicado: (2024)
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
por: Ding, Xuwei, et al.
Publicado: (2026)
por: Ding, Xuwei, et al.
Publicado: (2026)
Data Obfuscation for Secure Use of Classical Values in Quantum Computation
por: Raj, Amal, et al.
Publicado: (2026)
por: Raj, Amal, et al.
Publicado: (2026)
A Risk Estimation Study of Native Code Vulnerabilities in Android Applications
por: Sanna, Silvia Lucia, et al.
Publicado: (2024)
por: Sanna, Silvia Lucia, et al.
Publicado: (2024)
Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
por: Puppala, Sai, et al.
Publicado: (2026)
por: Puppala, Sai, et al.
Publicado: (2026)
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
por: Karthikeyan, Harish, et al.
Publicado: (2025)
por: Karthikeyan, Harish, et al.
Publicado: (2025)
The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
por: Xu, Zijie, et al.
Publicado: (2025)
por: Xu, Zijie, et al.
Publicado: (2025)
Quantifying Memory Cells Vulnerability for DRAM Security
por: Hu, Zilong, et al.
Publicado: (2026)
por: Hu, Zilong, et al.
Publicado: (2026)
Security Vulnerabilities in Ethereum Smart Contracts: A Systematic Analysis
por: Wu, Jixuan, et al.
Publicado: (2025)
por: Wu, Jixuan, et al.
Publicado: (2025)
Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents
por: Jiang, Linxi, et al.
Publicado: (2026)
por: Jiang, Linxi, et al.
Publicado: (2026)
A Systematic Review of Security Vulnerabilities in Smart Home Devices and Mitigation Techniques
por: Alzaylaee, Mohammed K.
Publicado: (2025)
por: Alzaylaee, Mohammed K.
Publicado: (2025)
Security Vulnerabilities in Quantum Cloud Systems: A Survey on Emerging Threats
por: Coupel, Justin, et al.
Publicado: (2025)
por: Coupel, Justin, et al.
Publicado: (2025)
Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
por: Haque, Md Wasiul, et al.
Publicado: (2025)
por: Haque, Md Wasiul, et al.
Publicado: (2025)
Mind the Web: The Security of Web Use Agents
por: Shapira, Avishag, et al.
Publicado: (2025)
por: Shapira, Avishag, et al.
Publicado: (2025)
Securing the Open RAN Infrastructure: Exploring Vulnerabilities in Kubernetes Deployments
por: Klement, Felix, et al.
Publicado: (2024)
por: Klement, Felix, et al.
Publicado: (2024)
BinPool: A Dataset of Vulnerabilities for Binary Security Analysis
por: Arasteh, Sima, et al.
Publicado: (2025)
por: Arasteh, Sima, et al.
Publicado: (2025)
Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
por: Liu, Hanzhi, et al.
Publicado: (2026)
por: Liu, Hanzhi, et al.
Publicado: (2026)
Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations
por: Babbush, Ryan, et al.
Publicado: (2026)
por: Babbush, Ryan, et al.
Publicado: (2026)
Systematic Assessment of Cache Timing Vulnerabilities on RISC-V Processors
por: Austa, Cédrick, et al.
Publicado: (2025)
por: Austa, Cédrick, et al.
Publicado: (2025)
Rigorous and Generalized Proof of Security of Bitcoin Protocol with Bounded Network Delay
por: Blake, Christopher, et al.
Publicado: (2026)
por: Blake, Christopher, et al.
Publicado: (2026)
Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
por: Lilienthal, Derek, et al.
Publicado: (2025)
por: Lilienthal, Derek, et al.
Publicado: (2025)
A Study on Web Application Vulnerabilities to find an optimal Security Architecture
por: Amuthadevi, C., et al.
Publicado: (2022)
por: Amuthadevi, C., et al.
Publicado: (2022)
The Elephant in the Room: Software and Hardware Security Vulnerabilities of Portable Sequencing Devices
por: Stillman, Carson, et al.
Publicado: (2024)
por: Stillman, Carson, et al.
Publicado: (2024)
Secure Change-Point Detection for Time Series under Homomorphic Encryption
por: Mazzone, Federico, et al.
Publicado: (2026)
por: Mazzone, Federico, et al.
Publicado: (2026)
Obfuscating Code Vulnerabilities against Static Analysis in JavaScript Code
por: Pagano, Francesco, et al.
Publicado: (2026)
por: Pagano, Francesco, et al.
Publicado: (2026)
Secure and Efficient Access Control for Computer-Use Agents via Context Space
por: Gong, Haochen, et al.
Publicado: (2025)
por: Gong, Haochen, et al.
Publicado: (2025)
Virtual Reality and Augmented Reality Security: A Reconnaissance and Vulnerability Assessment Approach
por: Dastgerdy, Sarina
Publicado: (2024)
por: Dastgerdy, Sarina
Publicado: (2024)
A Review on the Security Vulnerabilities of the IoMT against Malware Attacks and DDoS
por: Dzamesi, Lily, et al.
Publicado: (2025)
por: Dzamesi, Lily, et al.
Publicado: (2025)
SoK: What don't we know? Understanding Security Vulnerabilities in SNARKs
por: Chaliasos, Stefanos, et al.
Publicado: (2024)
por: Chaliasos, Stefanos, et al.
Publicado: (2024)
Ejemplares similares
-
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
por: Bullwinkel, Blake, et al.
Publicado: (2025) -
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
por: Bullwinkel, Blake, et al.
Publicado: (2026) -
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System
por: Munoz, Gary D. Lopez, et al.
Publicado: (2024) -
Securing AI Agents with Information-Flow Control
por: Costa, Manuel, et al.
Publicado: (2025) -
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
por: Pradhan, Gauri, et al.
Publicado: (2025)