无人机入侵检测中对话式与仪表盘式可解释人工智能：操作员信任与依赖的实证研究
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
浏览论文内容
中文总结 AI 辅助
本研究对比对话式与仪表盘式XAI界面对无人机入侵检测操作员信任和依赖的影响，发现对话式界面可用性更高但易引发过度依赖，为未来XAI系统设计提供启示。
中文摘要 AI 辅助
基于机器学习的入侵检测系统（IDS）已在保护无人机（UAV）网络方面展现出优异性能。然而，这些模型的“黑箱”特性，结合多模态网络物理数据的高维度，带来了重大的可解释性挑战。静态可视化仪表盘可能难以以操作员易于检查和解释的形式呈现多模态网络物理特征间的复杂关系。为解决这一问题，我们提出了一种由大语言模型（LLM）驱动的对话式XAI界面，以支持按需调查。在一项针对参与者的受控实验中，我们系统评估了该对话式界面与传统XAI仪表盘在事后审计任务中对操作员理解、信任和依赖的影响。我们的结果表明，对话式界面被认为比仪表盘更有用，这可能是因为它帮助参与者更轻松地获取和综合相关信息。然而，这一优势伴随着适当自我依赖水平的降低，表明存在过度依赖的潜在风险。一种可能的解释是，自然语言响应使AI建议更易被接受，这可能降低了参与者在IDS不正确时验证底层证据的倾向。这些发现指出了无人机入侵审计中人机协作的潜在权衡：提升感知可用性的交互机制也可能增加不当依赖的风险。最后，我们讨论了未来XAI系统的设计启示，这些系统需在无缝交互与认知强制功能之间取得平衡，以培养适当的依赖。
英文摘要
Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant interpretability challenges. Static visualization dashboards may struggle to present complex relationships among multimodal cyber-physical features in a form that is easy for operators to inspect and interpret. To address this, we propose a Conversational XAI interface powered by Large Language Models (LLM) to facilitate on-demand investigation. In a controlled experiment with participants, we systematically evaluated the impact of this conversational interface versus a traditional XAI Dashboard on operator understanding, trust, and reliance during post-incident auditing tasks. Our results suggest that the conversational interface was perceived as more useful than the dashboard, potentially because it helped participants access and synthesize relevant information more easily. However, this benefit was accompanied by a lower level of appropriate self-reliance, indicating a potential risk of over-reliance. One possible interpretation is that the natural-language responses made the AI advice easier to accept, which may have reduced participants' tendency to verify the underlying evidence when the IDS was incorrect. These findings point to a potential trade-off in human-AI collaboration for UAV intrusion auditing: interaction mechanisms that improve perceived usability may also increase the risk of inappropriate reliance. We conclude by discussing design implications for future XAI systems that balance seamless interaction with cognitive forcing functions to foster appropriate reliance.
发表机构
- Phenikaa University（菲卡大学）
- Phenikaa School of Computing（菲卡计算机学院）
- MobiFone Corporation（MobiFone集团）
- MobiFone HighTech Center（MobiFone高科技中心）
- National Economics University（国民经济大学）
- College of Technology（技术学院）
机构由 AI 辅助整理，请以论文原文为准。
