Attacking Vision-Language Computer Agents via Pop-ups

Shows that vision-language computer agents can be reliably distracted by adversarial pop-ups that human users would typically ignore. On OSWorld and VisualWebArena, these pop-ups achieve high attack success rates and sharply reduce task completion, while simple defenses like warning prompts remain ineffective.

• Dissecting Adversarial Robustness of Multimodal LM Agents
  June 18, 2024 · ICLR 2025 (Poster)
• Preference Redirection via Attention Concentration: An Attack on Computer Use Agents
  April 9, 2026 · arXiv
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
  January 14, 2026 · arXiv
• Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming
  October 21, 2025 · ICME 2026
• Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent
  August 6, 2025 · arXiv
• RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
  May 31, 2025 · NeurIPS 2025 (Poster)
• OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
  April 11, 2024 · NeurIPS 2024 Datasets and Benchmarks Track
• The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
  April 12, 2026 · arXiv
• IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
  April 6, 2026 · arXiv
• GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
  March 27, 2026 · arXiv
• Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
  March 4, 2026 · arXiv
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
  February 9, 2026 · arXiv
• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
  February 9, 2026 · arXiv
• EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
  January 22, 2026 · arXiv
• WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
  January 13, 2026 · arXiv
• It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
  December 29, 2025 · arXiv
• DECEPTICON: How Dark Patterns Manipulate Web Agents
  December 28, 2025 · arXiv
• Permission Manifests for Web Agents
  December 7, 2025 · arXiv
• Investigating the Impact of Dark Patterns on LLM-Based Web Agents
  October 20, 2025 · IEEE S&P 2026
• Watch and Learn: Learning to Use Computers from Online Videos
  October 6, 2025 · CVPR 2026
• Scaling Agents for Computer Use
  October 2, 2025 · arXiv
• WALT: Web Agents that Learn Tools
  October 1, 2025 · ICLR 2026 (Poster)
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
  September 28, 2025 · arXiv
• ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
  August 19, 2025 · ICLR 2026 (Poster)