Dark Patterns 遇见 GUI 智能体：LLM 智能体对操纵性界面的易感性及人类监督的作用
Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
AI总结：
研究通过两阶段实验考察了LLM驱动的GUI智能体、人类及人机团队对16种dark patterns的响应，发现智能体易因程序盲点受操纵且人类监督虽能提升规避率但会引入认知成本，揭示了协作新漏洞并呼吁透明与可调自主性设计。
摘要：
Dark patterns（操纵用户行为的欺骗性界面设计）对人类决策和自主性的影响已被广泛研究。然而，随着由 LLM 驱动的 GUI 智能体（从高层意图自动化任务）日益普及，理解 dark patterns 如何影响智能体变得愈发重要。我们提出了一项两阶段的实证研究，考察智能体、人类参与者及人机团队在多样场景下对 16 种 dark patterns 的响应。阶段 1 表明，智能体常无法识别 dark patterns，即便察觉，也会将任务完成置于保护性操作之上。阶段 2 揭示了不同的失败模式：人类因认知捷径和习惯性顺从而屈服，智能体则因程序性盲点而失误。人类监督提高了规避率，但引入了注意力隧道和认知负荷等成本。研究结果表明，人类和智能体均非一致地具备抗性，且协作引入了新漏洞，提示设计需关注透明度、可调自主性和监督。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
