DECEPTICON:暗模式如何操纵网络代理
DECEPTICON: How Dark Patterns Manipulate Web Agents
AI总结:
DECEPTICON研究揭示暗模式通过引导代理轨迹对网络代理构成重大风险,表明需加强防御措施以应对操纵性设计。
摘要:
欺骗性用户界面设计,广泛存在于网络上,通常被称为暗模式,会迫使用户执行与其目标不一致的操作。在本文中,我们展示了暗模式在引导代理轨迹方面非常有效,对代理的鲁棒性构成了重大风险。为了量化这一风险,我们引入了DECEPTICON,一个用于单独测试个体暗模式的环境。DECEPTICON包含700个网络导航任务,其中包含暗模式——600个生成的任务和100个现实世界任务,旨在衡量遵循指示的成功率和暗模式的有效性。在最先进的代理中,我们发现暗模式在超过70%的测试生成和现实世界任务中成功将代理轨迹引导向恶意结果——相比人类平均的31%。此外,我们发现暗模式的有效性与模型大小和测试时推理呈正相关,使更大、能力更强的模型更容易受到攻击。领先的对抗攻击防御措施,包括上下文提示和防护模型,未能一致地降低暗模式干预的成功率。我们的发现揭示了暗模式作为潜在且未被缓解的风险,对网络代理构成威胁,突显了对操纵性设计进行稳健防御的紧迫需求。
英文摘要:
Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned with their goals. In this paper, we show that dark patterns are highly effective in steering agent trajectories, posing a significant risk to agent robustness. To quantify this risk, we introduce DECEPTICON, an environment for testing individual dark patterns in isolation. DECEPTICON includes 700 web navigation tasks with dark patterns -- 600 generated tasks and 100 real-world tasks, designed to measure instruction-following success and dark pattern effectiveness. Across state-of-the-art agents, we find dark patterns successfully steer agent trajectories towards malicious outcomes in over 70% of tested generated and real-world tasks -- compared to a human average of 31%. Moreover, we find that dark pattern effectiveness correlates positively with model size and test-time reasoning, making larger, more capable models more susceptible. Leading countermeasures against adversarial attacks, including in-context prompting and guardrail models, fail to consistently reduce the success rate of dark pattern interventions. Our findings reveal dark patterns as a latent and unmitigated risk to web agents, highlighting the urgent need for robust defenses against manipulative designs.
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。