DARPA BioSEC: Detection and Mitigation Intelligent Agent Network (DaMIAN)

Abstract

The goal of the Detection and Mitigation Intelligent Agent Network (DaMIAN) effort is to develop human immune system (HlS)-inspired, antibody-like intelligent agents capable of detecting and mitigating hardware trojan attacks via the use of neuromorphic computational System-on-Chip (SoC) modules. This includes: Baselining the SoC [Body] through monitoring of network-on-chip (NoC) transactions, Detecting rare events [Invaders] in NoC traffic, and Monitoring and Overruling [Surround and Attack] untrusted SoC modules through behavioral prediction, e.g. modeling or fingerprinting. This report provides relevant background information, in Section 2, which attempts to link elements of the human immune system to the DaMIAN effort. It also outlines the progress made during execution of the three month effort including the Literature Review, Technical Opportunity Analysis, and Simulations which are detailed in Sections 3, 4, and 5 respectively.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 25, 2021
Accession Number
AD1124458

Entities

People

  • William Suski

Tags

Communities of Interest

  • Advanced Electronics
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Application-Specific Integrated Circuits
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Central Processing Units
  • Computational Science
  • Computer Programming
  • Computer Programs
  • Computers
  • Deep Learning
  • Department Of Defense
  • Dimensionality Reduction
  • Engineering
  • Field Programmable Gate Arrays
  • Information Science
  • Intelligent Agents
  • Machine Learning
  • Network Architecture
  • Neural Networks
  • Supervised Machine Learning

Readers

  • Cybersecurity.
  • Data Mining and Knowledge Discovery.
  • Distributed Systems and Data Platform Development