研究大模型代理如何被欺骗性界面操纵，发现人与机器都易受影响。
Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
- 通过实验测试16类欺骗性设计对代理的影响
- 代理常忽视欺骗行为，优先完成任务而非防御
- 人类监督虽能提升防护，但增加注意力负担
暗模式（dark patterns）——一种操纵用户行为的欺骗性界面设计——已被广泛研究其对人类决策和自主性的负面影响。然而，随着大语言模型驱动的GUI代理在自动化高阶任务中日益普及，理解暗模式对这些代理的影响变得愈发重要。我们开展两阶段实证研究，考察代理、人类参与者以及人机协作团队在多种场景下对16类暗模式的响应。第一阶段表明，代理往往无法识别暗模式，即便察觉也倾向于以任务完成为优先，忽略保护性行为。第二阶段揭示了不同的失败模式：人类因认知捷径和习惯性服从而受骗，代理则因程序盲点而失效。人类监督虽提升了规避能力，但也带来注意力隧道效应和认知负荷等代价。研究显示，人与代理均非全然抗脆弱，协作反而引入新漏洞，提示需在系统设计中强化透明度、可调节自主性和监督机制。
原文摘要 · Abstract (English)
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。