Research – SAIL Lab

Research At SAIL

The Secure and Assured Intelligent Learning (SAIL) lab works towards laying concrete foundations for the safety and security of intelligent machines with both theoretical and engineering perspectives. Our research aspires to develop comprehensive models, metrics, frameworks, and tools for analysis, implementation, and mitigation of deleterious behaviors in AI systems.

CONSTRAINED RANDOMIZATION OF POLICY (CROP)

Combating Human Trafficking via Automated Intelligence Collection, Validation, and Fusion

Compromising Trading Deep Reinforcement Learning Agents

Fault Detection and Prognosis in Medical Devices

Adversarial Manipulation of EEG-Based BCI

Adversarial Manipulation of Automated OSINT Solutions

Hybrid Deep Learning Model for Fake News Detection in Social Networks

DEFENSE AGAINST ADVERSARIAL COMMUNICATION IN MULTI-AGENT REINFORCEMENT LEARNING

Adaptive Discount Factor in Reinforcement learning

Automated Penetration Testing using Reinforcement Learning

Security of Distributed Networks

Fake News Detection

Fake News Detection using Deep Learning Models

New Source Identification in Twitter Data Steam Using Community Detection

Security of Deep Reinforcement Learning

Automated Collection and Analysis of Open-Source Cyber Threat Intelligence

Security of Complex Adaptive Systems

Ethical Decision-Making in AI

Security of Unmanned Vehicles

ADVERSARIAL MACHINE LEARNING ON LICENSE PLATE RECOGNITION

Automatic Podcast Generation

Cyber Intrusion Detection and Prediction

Machine Learning and Game Theory for Counter-Terrorism

Intelligent Mobile Robotics

Secured Citation Assistant using NLP techniques

Drone Detection Using mmWave Radar

AMBLY: SMART DARKNET SPIDER

AI Safety