Skip to main content
TRUST

Research Thrust

AI Security, Cyber Defense & Forensics

Understanding how intelligent systems are attacked, defended, and investigated — from adversarial machine learning to digital forensics of AI-driven incidents.

As machine learning models are deployed into networks, critical infrastructure, and autonomous decision-making pipelines, they introduce a new and rapidly evolving attack surface. This thrust studies the offensive and defensive dimensions of AI security, along with the forensic methods needed to investigate incidents involving intelligent systems.

Research directions include:

  • Adversarial machine learning: evasion, poisoning, model extraction, and membership inference attacks and defenses
  • AI-enabled cyber defense: intrusion detection, anomaly detection, and threat intelligence using machine learning
  • Digital forensics and incident response for AI-driven and AI-targeted systems
  • Robustness evaluation and red-teaming methodologies for deployed models

The objective is to build intelligent systems that anticipate, withstand, and recover from malicious manipulation, and to develop rigorous forensic techniques for investigating AI-related security incidents.

Related Work

Publications in this Area

Conference Submitted

Manuscript submitted — under peer review; not yet published.

FedTrace: Forensic Client Attribution and Attack-Onset Localization in Heterogeneous Federated Learning

Al Amin

NDSS 2027, 2027

AI Security, Cyber Defense & ForensicsSecure & Privacy-Preserving Distributed Intelligence
Cite this work

Al Amin. "FedTrace: Forensic Client Attribution and Attack-Onset Localization in Heterogeneous Federated Learning." Submitted to NDSS 2027.

Conference Published

SENTINEL: A Multi-Pathway Architecture for Detecting Living-off-the-Land APT Attacks on Windows Command Lines

Al Amin

IEEE Military Communications Conference (MILCOM), 2026

AI Security, Cyber Defense & Forensics
Cite this work

Al Amin. "SENTINEL: A Multi-Pathway Architecture for Detecting Living-off-the-Land APT Attacks on Windows Command Lines." IEEE Military Communications Conference (MILCOM), 2026.

← Back to all research areas