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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zelin, Yoon, Han Jun, Alluru, Nithin, Moore, Terrence J., Nelson, Frederica F., Yoon, Seunghyun, Lim, Hyuk, Kim, Dan Dongseong, Cho, Jin-Hee
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909972626931712
author Wan, Zelin
Yoon, Han Jun
Alluru, Nithin
Moore, Terrence J.
Nelson, Frederica F.
Yoon, Seunghyun
Lim, Hyuk
Kim, Dan Dongseong
Cho, Jin-Hee
author_facet Wan, Zelin
Yoon, Han Jun
Alluru, Nithin
Moore, Terrence J.
Nelson, Frederica F.
Yoon, Seunghyun
Lim, Hyuk
Kim, Dan Dongseong
Cho, Jin-Hee
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18616
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System
Wan, Zelin
Yoon, Han Jun
Alluru, Nithin
Moore, Terrence J.
Nelson, Frederica F.
Yoon, Seunghyun
Lim, Hyuk
Kim, Dan Dongseong
Cho, Jin-Hee
Human-Computer Interaction
Artificial Intelligence
Cryptography and Security
Multiagent Systems
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.
title DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System
topic Human-Computer Interaction
Artificial Intelligence
Cryptography and Security
Multiagent Systems
url https://arxiv.org/abs/2512.18616