Abstract
Deep learning finds rich applications in the tactical domain by learning from diverse data sources and performing difficult tasks to support mission-critical applications. However, deep learning models are susceptible to various attacks and exploits. In this paper, we first discuss application areas of deep learning in the tactical domain. Next, we present adversarial machine learning as an emerging attack vector and discuss the impact of adversarial attacks on the deep learning performance. Finally, we discuss potential defense methods that can be applied against these attacks.
Recommended Citation
Fields, Dr. DeNaria; Friend, Shakiya A.; Hermansen, Andrew; Erpek, Dr. Tugba; and Sagduyu, Dr. Yalin E.
(2024)
"Machine Learning Security for Tactical Operations,"
Military Cyber Affairs: Vol. 7
:
Iss.
1
, Article 3.
Available at:
https://digitalcommons.usf.edu/mca/vol7/iss1/3
Included in
Computer and Systems Architecture Commons, Digital Communications and Networking Commons, Military, War, and Peace Commons, Other Computer Engineering Commons, Systems Science Commons
