Machine Learning 5G Attack Detection in Programmable Logic

Conference · Thu Jan 12 04:00:00 EST 2023

OSTI ID:1975113

Anderson, Matthew William ^[1]; Coldwell, Cooper Wayne ^[1]; Sgambati, Matthew R ^[1]; Jacobson, Brendan Glen ^[1]; Petersen, Bryton John ^[1]; Spencer, Damon Renel ^[1]; Conger, Denver Shane ^[1]; Goodell, Edward ^[1]

---

1. Idaho National Laboratory

Machine learning-assisted network security may significantly contribute to securing 5G components. However, machine learning network security inference speeds generally require tens to hundreds of milliseconds thereby introducing significant latency in 5G operations. The inference latency can be reduced by deploying the machine learning model to programmable logic in a field programmable gate array (FPGA) at the cost of a small loss in accuracy. In order to quantify this loss, as well as to establish baseline performance inference speeds for programmable logic implementations, this work explores an autoencoder and a ß-variational autoencoder deployed on two different FPGA evaluation boards and compares accuracy and performance against an NVIDIA A100 GPU implementation. A publicly available 5G dataset containing 10 types of attacks along with normal traffic is introduced as part of the evaluation.

• Research Organization: Idaho National Laboratory (INL), Idaho Falls, ID (United States)
• Sponsoring Organization: USDOE Office of Nuclear Energy (NE)
• DOE Contract Number: AC07-05ID14517
• OSTI ID: 1975113
• Report Number(s): INL/CON-22-68438-Rev002
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
FPGA
machine learning