arXiv：cs.AI· Cong Chi Nguyen, Trang Mai Xuan, Vu-Duc Ngo, Kim-Ngan Thi Nguyen, Trong-Nghia Nguyen, Thien Van Luong·· 3 小时前
论文撤稿：LLM 对话式 XAI 与仪表盘 XAI 用于无人机入侵检测的对比研究
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
AI 导读
一篇研究 LLM 对话式 XAI 界面与静态仪表盘对 UAV 入侵检测操作员信任与依赖影响的论文被作者撤稿，原因是实验数据存在关键错误，导致主要结论不成立。原研究曾发现对话界面被认为更有用，但伴随更低的适度自主依赖，存在过度依赖风险。
正文
This paper has been withdrawn by Nguyen Cong Chi
No PDF available, click to view other formats
Abstract: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.
| Comments: | We have discovered a critical error in our experimental data that invalidates the main conclusions |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.10434 [cs.AI] |
| (or arXiv:2608.10434v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.10434 arXiv-issued DOI via DataCite |
Submission history
From: Nguyen Cong Chi [view email]
[v1]
Tue, 11 Aug 2026 03:31:59 UTC (811 KB)
[v2]
Thu, 8 Oct 2026 14:13:27 UTC (1 KB) (withdrawn)
来源：arXiv：cs.AI · arxiv.org