DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System

TL;DR

DASH introduces a deception-based framework that enhances mission resilience in human-machine teams by detecting insider threats through bait tasks and enabling adaptive recovery, significantly improving success rates under attack.

Contribution

The paper presents DASH, a novel framework integrating proactive deception into shared mental models for improved security and coordination in human-machine teaming.

Findings

DASH maintains about 80% mission success under high attack rates.

DASH outperforms SMM-only, no-SMM, and baseline schemes by eight times in robustness.

Empirical evaluations validate DASH's effectiveness in adversarial scenarios.

Abstract

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.