Back to Search Start Over

Exploring Potential Prompt Injection Attacks in Federated Military LLMs and Their Mitigation

Authors :
Lee, Youngjoon
Park, Taehyun
Lee, Yunho
Gong, Jinu
Kang, Joonhyuk
Publication Year :
2025

Abstract

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new threats that may undermine operational security, disrupt decision-making, and erode trust among allies. This perspective paper highlights four potential vulnerabilities in federated military LLMs: secret data leakage, free-rider exploitation, system disruption, and misinformation spread. To address these potential risks, we propose a human-AI collaborative framework that introduces both technical and policy countermeasures. On the technical side, our framework uses red/blue team wargaming and quality assurance to detect and mitigate adversarial behaviors of shared LLM weights. On the policy side, it promotes joint AI-human policy development and verification of security protocols. Our findings will guide future research and emphasize proactive strategies for emerging military contexts.<br />Comment: 7 pages

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2501.18416
Document Type :
Working Paper