• Secure and Assured Intelligent Learning (SAIL) Lab

    @ University of New Haven

    About Us
  • Secure and Assured Intelligent Learning (SAIL) Lab

    @ University of New Haven

    About Us
  • Secure and Assured Intelligent Learning (SAIL) Lab

    @ University of New Haven

    About Us

About Us

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.

In The Media

October 14, 2024 Four in critical condition after crash In a recent NBC Connecticut feature, Dr. Vahid Behzadan, assistant professor …
October 14, 2024 Four in critical condition after crash In a recent NBC Connecticut feature, Dr. Vahid Behzadan, assistant professor …
September 06, 2024 AI and Job Applications Dr. Vahid Behzadan, assistant professor of cybersecurity, data and computer science, and director …
10 Oct 2023 Newsday : Jake’s 58 customers should monitor accounts after cybersecurity breach that closed casino, experts say 📰 …

Latest Events

Presenters: Bibek Upadhata (Ph.D. Candidate SAIL LAB)Time: Friday 10/11/2024, 4:00 PM – 5:00 pm ETPlace: Maxcy 233ARecording: EFFICIENT AND ROBUST LANGUAGE ADAPTATION IN MULTILINGUAL …
Presenters: Seyed Sajjadi (Founder & CEO nFlux AI, NASA Engineer, Artificial Intelligence Consultant), Time: Monday 04/17/2023, 3:30 PM – 4:30 …

News

The University’s SAIL (Systems, Automation, and Intelligence Lab) is at the forefront of pioneering research, providing a dynamic platform for …
🔬 Exciting Announcement: Binesh and Bahareh’s Research Paper on Early Failure Detection in Medical Devices Accepted at ICMHI 2024! 🌐 …
Dr. Vahid Behzadan, the director of the SAIL lab, has been appointed to the newly formed Connecticut Artificial Intelligence Task …
SAIL LAB, University of New Haven – Jul 7, 2023 We are thrilled to share the remarkable news that Nancirose …

Automated Penetration Testing using Reinforcement Learning

We aim to use Reinforcement Learning to allow an agent to be able to conduct penetration tests without a human operator.

read more

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

We aim to leverage the artificial intelligence and machine learning methods for intelligence analysis to combat Human Trafficking.

read more

Automated Collection and Analysis of Open-Source Cyber Threat Intelligence

We develop machine learning models to collect data from sources such as social media, news websites, forums, and the darknet to discover and identify indicators of threat.

read more

Machine Learning for Cybersecurity

We study and develop reliable and scalable machine learning techniques to identify vulnerabilities, detect malicious behavior, and prevent attacks.

read more

FAULT DETECTION AND PROGNOSIS IN MEDICAL DEVICES

The medical device industry is leaping forward by relying on electronics to improve life-saving medical devices’ safety and performance.

read more

ADVERSARY ENGAGEMENT ONTOLOGY

Adversary Engagement Ontology (AEO) is a subset of the Unified Cyber Ontology that aims to define and standardize the representation of

read more

ADVERSARIAL ATTACK ON EEG-BASED BCI DEVICES

This project investigates whether Motor Imagery (MI) BCIs are vulnerable to Adversarial Stimuli, which are minor sensory perturbations.

read more

DECEPTION IN MULTI-AGENT SYSTEMS

Multi-Agent Systems (MAS) is the study of multi-agent interactions in a shared environment. Communication for cooperation is a fundamental construct for sharing information in partially observable environments

read more