用诱饵任务提前发现团队内鬼，提升人机协作安全性
DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System
- 在共享心智模型中加入主动欺骗机制，识别潜在内部威胁
- 高攻击环境下仍保持80%任务成功率，是基线的8倍
- 适合安防、救援等关键任务场景，尤其关注内部风险
我们提出DASH（Deception-Augmented Shared Mental Model for Human-machine teaming），一种通过在共享心智模型（SMM）中嵌入主动欺骗来增强任务韧性的新框架。针对监控与救援等关键任务，DASH引入“诱饵任务”以提前检测内部威胁，如被攻陷的无人地面车辆（UGVs）、AI代理或人类分析员。一旦检测到威胁，将触发定制化恢复机制，包括重装UGV系统、重新训练AI模型或替换人类分析师。相比忽略内部风险的传统SMM方法，DASH同时提升了协调性与安全性。在四种方案（DASH、仅SMM、无SMM和基线）的实证评估中，DASH在高攻击率下仍维持约80%的任务成功率，是基线的八倍。本工作贡献了一个基于共享心智模型的人机协作框架，一种基于欺骗的内鬼检测策略，以及对抗环境下鲁棒性增强的实证证据。DASH为对抗环境中安全、自适应的人机协同奠定了基础。
原文摘要 · Abstract (English)
We present DASH (Deception-Augmented Shared mental model for Human-machine teaming), a novel framework that enhances mission resilience by embedding proactive deception into Shared Mental Models (SMM). Designed for mission-critical applications such as surveillance and rescue, DASH introduces "bait tasks" to detect insider threats, e.g., compromised Unmanned Ground Vehicles (UGVs), AI agents, or human analysts, before they degrade team performance. Upon detection, tailored recovery mechanisms are activated, including UGV system reinstallation, AI model retraining, or human analyst replacement. In contrast to existing SMM approaches that neglect insider risks, DASH improves both coordination and security. Empirical evaluations across four schemes (DASH, SMM-only, no-SMM, and baseline) show that DASH sustains approximately 80% mission success under high attack rates, eight times higher than the baseline. This work contributes a practical human-AI teaming framework grounded in shared mental models, a deception-based strategy for insider threat detection, and empirical evidence of enhanced robustness under adversarial conditions. DASH establishes a foundation for secure, adaptive human-machine teaming in contested environments.
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。