ANTA: Machine Learning vs. Deep Learning for Network Traffic Analysis

ANTA (Accelerated Network Traffic Analytics) was ADAL’s SCARP 2020 project, A Performance Study between Machine Learning and Deep Learning Methods on Network Traffic Analysis.

The team studied the problem of detecting TLS-encrypted malware using flow metadata and TLS features. They benchmarked a suite of widely used machine learning and deep learning models on two malware flow datasets, measuring classification accuracy as well as run-time performance (throughput, CPU and RAM utilization), and accelerated the detectors with Intel DAAL and OpenVINO.

Team

  • Matthew Grohotolski and Connor DiLeo, student researchers
  • Dr. Peilong Li, faculty mentor
  • Collaborators: Dr. Yan Luo and Onur Barut (University of Massachusetts Lowell) and Tong Zhang (Intel)
Avatar
ADAL
Department of Computer Science

The Agentic and Dependable AI Lab (ADAL) is an undergraduate research lab at Elizabethtown College working on AI for cybersecurity, edge AI, large language models and privacy-preserving machine learning.

Related