Module Overview

This course introduces students to the application of machine learning techniques in modern cybersecurity systems. It covers fundamental machine learning concepts, including supervised, semi-supervised, unsupervised, and reinforcement learning, as well as neural networks and deep learning, with a focus on cybersecurity use cases. Students learn how to select and apply appropriate models for tasks such as malware classification, botnet detection, and intrusion detection.

The course further explores adversarial machine learning, examining attacks on data and models during both training and deployment, along with practical defenses and mitigation strategies. It also addresses generative AI security, secure MLOps practices, and the legal and ethical considerations involved in collecting and using security-related data. Through real-world examples and hands-on exercises, students gain a strong foundation in designing, deploying, and defending machine learning–based cybersecurity solutions for research and industry applications.

Topics

1. Foundations of Machine Learning for Cybersecurity

• Overview of supervised learning models
• Logistic regression, Naive Bayes, neural networks, and deep learning
• Overview of unsupervised learning models
• Principal Component Analysis (PCA), K-means clustering, and Gaussian Mixture Models
• Live demonstration: Building an end-to-end machine learning pipeline

2. Data-Driven Network and Computer Security

• Internet architecture and network traffic measurement
• Traffic behavior analysis and anomaly detection
• Live demonstration: Network traffic analysis using unsupervised learning techniques
• Applications of machine learning in network security
• Supervised learning use cases: Spam filtering and phishing detection
• Unsupervised learning use cases: Network anomaly detection

3. Machine Learning in Adversarial Environments

• Introduction to adversarial machine learning and threat modeling
• Adversarial manipulation of machine learning systems
• Example: Distorting personalization systems
• Defense strategies against adversarial attacks
• Example: Evasion of intrusion and attack detection systems

4. Ethics, Fairness, and Responsible AI in Cybersecurity

• Fairness, transparency, and explainability in cybersecurity ML models
• Privacy concepts and practical implementation in industry settings
• Externalities and real-world implications of ML errors in cybersecurity
• Responsible data collection, usage, and lifecycle management
• Hands-on lab: Fraudulent account detection using a virtual case study

5. Secure Machine Learning Development and Deployment

• Secure design principles for ML-based cybersecurity systems
• Model validation, deployment, and monitoring considerations
• Capstone case study: Real or hypothetical ML-driven cybersecurity deployment
• Individualized faculty feedback and strategic guidance

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

Module Overview

This course introduces students to major categories of malicious software that harm users and computer systems, including viruses, Trojan horses, worms, rootkits, scareware, and spyware. The course begins with the fundamentals of reverse engineering and progressively covers advanced attack techniques employed by modern malware. Students will also examine practical countermeasures used in real-world production systems. Through hands-on analysis of real malware samples, the course provides a strong foundation for students interested in cybersecurity research, academia, and industry practice.

Topics

1. Principles and Fundamental Concepts

• Assembly languages and program compilation
• Binary code and ELF/PE data representations
• Static binary analysis and disassembly
• Dynamic execution analysis

2. Attacks and Existing Malware

• Malware behavior (e.g., control flow hijacking)
• Anti-reverse engineering and obfuscation
• Return-oriented programming
• Web-based malware and social engineering

3. Analyze vulnerabilities in AI systems.

• Symbolic execution and taint tracking
• Runtime memory forensics
• Behavioral detection signatures
• Security hardening (ASLR, DEP, and CFI)

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

Module Overview

This program provides fundamental security primitives specific to cyber-physical systems and to apply them to a broad range of current and future security challenges, as well as introductions on cyber physical security concepts, assessment of security flaws and threats to CPS, AI enabled threat detection and mitigation for CPS, Privacy-preserving secure solutions for CPS (e.g. smart grids), and risk management of CPS. Students will learn the modeling, design and implementation, and analysis of CPS safety-critical infrastructures, including but not limited to power grid, automobile, manufacturing, and their safety/security requirements in real-world settings. Smart grids are utilized as an example of CPS. MATPOWER on Matlab is utilized as a simulation tool. False data injection attacks (FDIAs) are simulated and implemented on IEEE-14 bus systems to simulate attacks on smart grids. Traditional detection methods, such as Bad Data Detector and machine learning-based detectors such as MLP, Decision Tree and Graph neural networks are both introduced and simulated for detecting FDIAs on smart grids.

This course includes hands-on labs focused on cyber-physical system security, including threat detection and AI-based attack detection. Students will simulate false data injection attacks (FDIAs) on smart grids using MATLAB's MATPOWER and explore detection methods, from traditional approaches to machine learning-based techniques.

Topics

1. Introduction to Cyber-Physical System (CPS) Security

• Overview of CPS and their integration in critical infrastructures such as power grids, automobiles, and manufacturing.

2. Security Threats and Risk Assessment in CPS

• Introduction to key security challenges in CPS.
• Case studies on real-world CPS vulnerabilities and attack scenarios.

3. Case studies on real-world CPS vulnerabilities and attack scenarios.

• Traditional security detection methods such as Bad Data Detectors (BDD).
• Implementation of rule-based security frameworks for anomaly detection.

4. AI-Enabled Threat Detection in CPS

• Introduction to AI-based models for anomaly detection in CPS environments.

5. False Data Injection Attacks (FDIAs) simulation on Smart Grids

• Simulation of FDIAs on the IEEE 14-bus system using MATPOWER in MATLAB.

6. Machine Learning-Based Detection of CPS Attacks

• Training and evaluating machine learning models (MLP, Decision Trees) for attack detection.

7. Graph Neural Networks for CPS Security

• Application of utilizing Graph Neural Networks (GNNs) in on smart grids.

8. AI-Enabled Cybersecurity Attacks in CPS

• Utilization on generative models such as Generative Adversarial Networks (GANs) to build new FDIAs attack.

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

Module Overview

This training module is being developed based on Cybersecurity Frameworks provided by government agencies, particularly drawing from the standardization documentation developed by NIST (National Institute of Standards and Technology). The NIST cybersecurity framework, NICE (National Initiative for Cybersecurity Education), which serves as a reference for describing and sharing information about cybersecurity work, is being used as the basis for shaping the training content for workforce upskilling in this module. The development of the training module is structured into five stages: Identify, Protect, Detect, Respond, and Monitor. Training contents for each step have been documented.

Topics

• Introduction to industrial control systems
• Threat landscape for industrial control systems
• Risk assessment and management
• Security standards and regulations
• Access control and authentication
• Network security for industrial control systems
• Security of industrial control systems components
• Incident response and recovery
• Security awareness and training
• Future trends and emerging technologies
• Case studies and practical exercises
• Final assessment and certification

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

Module Overview

Creating digital twins of intelligent manufacturing systems for cyber threat assessment is a proactive approach to enhancing the security of industrial operations. A digital twin is a virtual replica of a physical system, and in the context of smart manufacturing, it can represent the entire production process or individual components. By creating and maintaining digital twins for cyber threat assessment, you can proactively identify and mitigate vulnerabilities in your smart manufacturing system, enhancing the overall security of your industrial operations. This approach helps reduce the risk of cyberattacks and their potential impact on production, safety, and data integrity. The course is designed to provide students with an introductory understanding of digital twin technology in manufacturing applications. Students will study application models while gaining practical, hands-on experience with digital twin technology.

Topics

• Smart factory and Industry 4.0
• ISO standard on safety of machinery (cybersecurity aspects)
• Risk assessment and risk reduction
• Simulation and digital twin modeling and their building blocks
• Cyber threat modeling
• Incident response simulation
• Data collection and interfaces
• Virtual commissioning
• Running experiments and analysis
• Creating dashboards for data visualization
• Translating results to optimize factories
• Regulatory compliance and industry standards

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

Module Overview

The training teaches participants how to perform cyberattack prediction modeling in Cyber-Physical Systems (CPS) using digital twins. It will cover replicating physical devices, firmware, software, and their interactions within a digital twin framework. Participants will learn how digital twins can enhance the security of a company’s physical assets and strategies. The module includes hands-on practice with an industry use case, such as automotive or manufacturing. The training will focus on intelligence-driven digital twins that integrate data analytics and threat intelligence to simulate cyber threats to physical systems. Participants will learn methods to protect these systems. Two guided lab sessions are part of the course. Attendees will have VPN access to the lab infrastructure, enabling them to complete three lab assignments at their convenience.

The course teaches participants how digital twins can enhance the security of a company’s physical assets and strategies. The training will focus on intelligence-driven digital twins that integrate data analytics and threat intelligence to simulate cyber threats to physical systems. The module includes hands-on practice with an industry use case, such as automotive or manufacturing.

Topics

• Introduction to Cyber-Physical Systems
• Introduction to Digital Twins in CPS
• AI-Enabled Digital Twins for CPS
• Threat Detection and Mitigation using Digital Twins
• Digital Twin Cybersecurity Framework
• Hands-on Lab: Building and Securing a CPS Digital Twin
• Regulatory Framework and Compliance
• Future Trends in CPS Security through Digital Twins

Schedule

Start Date	End Date	Days	Times
12/15/25	1/5/26	M-Su	Synchronous Online, Anytime
1/15/26	2/15/26	M-Su	Synchronous Online, Anytime
3/1/26	4/1/26	M-Su	Synchronous/Asynchronous Online, Anytime

We'd love to hear from you

If you have questions about the programs, registration, or funding, please reach out. You can fill out our official inquiry form below, our team will get back to you shortly.

Open Contact Form