Certificate in AI for Cybersecurity
Start anytime. Learn at your own pace.
Build and deploy tools to defend against modern (and future) threats.
Designed and taught by Dr. Lanier Watkins from JHU Applied Physics Laboratory
LIVE monthly seminars and office hours
Engaging learning including video walkthroughs and hands-on activities
Satisfaction guaranteed. Explore the course with no risk.
Save $300 with the Certificate vs. buying courses separately
Attack surfaces are expanding. Malware is evolving. Alert fatigue is real.
The answers to the modern cybersecurity threats aren’t in firewalls and known signatures—they’re in spotting patterns no human can see and adapting in real time.
In this 3-course certificate program, Dr. Lanier Watkins gives Tier 1 and Tier 2 analysts the knowledge to use AI as a force multiplier and take your career to the next level.
His daily work at the Applied Physics Laboratory Infrastructure Protection Group AND role as Hopkins Engineering’s cybersecurity master’s program chair makes Dr. Watkins the ideal guide for a self-paced program combining academic rigor with real-world implementation.
Powered by Engineering for Professionals
The #1 Ranked Online Grad Program for Computer Information Technology by U.S. News & World Report
Johns Hopkins Engineering’s Lifelong Learning delivers executive education courses from the same faculty and support team behind Johns Hopkins Engineering for Professionals, the nation’s #1 online, part-time graduate program in computer information technology. This ranking includes our master’s programs in computer science, artificial intelligence, cybersecurity, information systems engineering, and data science.
Dr. Watkins will start you off with a solid foundation: realistic expectations for AI in cybersecurity; core types of machine learning; weak vs. strong vs. super AI. Then he’ll show you how to apply AI and machine learning to some of cybersecurity’s toughest challenges:
Spam and phishing at scale
Polymorphic and metamorphic malware
Botnet activity and command-and-control detection
Alert overload and noisy data
AI-attacks poisoning AI models
and develop working tools to defeat them.
It’s a grounded, project-based experience based in a secure virtual environment preloaded with Jupyter notebooks, working Python code, and real-world datasets. Dr. Watkins explains the concepts in video lectures and shares his favorite papers and articles. The preloaded notebooks get you started quickly while still giving you the freedom to solve and experiment.
You’ll explore techniques like supervised and unsupervised learning, anomaly detection, neural networks, and reinforcement learning—not just to understand the algorithms, but to wield them.
Along the way, you’ll build intuition around when to use each approach, how to evaluate their performance, and what their outputs really mean for decision-making. You’ll also dive into biometric authentication, fraud prevention, malware analysis, and intrusion detection.
You don’t need a background in math or data science. You’ll do what you do best as a cybersecurity analyst: developing and deploying tools—not designing the math behind them.
The Certificate combines Dr. Watkins’ 3 sequential cybersecurity courses:
into one bundle, saving you $300 off the cost of buying separately
Earning Your Certificate
After completing the course content, you can successfully complete and submit a capstone project to earn your Certificate of Achievement—proving to colleagues and employers that you’re ready to take the lead in building, evaluating and deploying cutting-edge AI cybersecurity solutions to protect critical assets.
The capstone requires applying all skills from the 3-course certificate into a single deliverable that demonstrates knowledge of state-of-the-art ML and includes sufficient performance metrics. The project will be reviewed by Dr. Watkins, who will provide feedback, which can be discussed further during live office hours.
The image is for illustrative purposes only. Actual certificate design subject to change,
No Risk: Satisfaction Guaranteed
Feel confident in your learning journey! If the certificate content is too advanced, not advanced enough, or simply doesn’t meet your expectations, we’ve got you covered with our money-back guarantee. Just contact our team within 7 days from purchase to receive a full refund—no questions asked.
Meet Your Instructor
Dr. Lanier Watkins
Johns Hopkins University, Johns Hopkins Applied Physics Laboratory
Lanier Watkins is Principal Professional Staff in the Critical Infrastructure Protection Group at the Johns Hopkins Applied Physics Laboratory, Assistant Technical Director of the Johns Hopkins Information Security Institute, and Chair of Johns Hopkins Engineering’s #1 ranked online master’s programs in Computer Science and Cybersecurity. He earned his PhD in computer science from George State University.
Dr. Watkins is Here to Help!
Questions about course content? Looking for insight on specific cyberthreats? Stop by monthly Zoom office hours to talk with Lanier and fellow students about what you’re learning in the course and the past, present, and future of cybersecurity.
Prerequisites
The Certificate is designed for cybersecurity professionals and experienced students. A foundational knowledge of Python is required, as this course involves modifying algorithms and adjusting parameters to better understand their implementation. You don’t need to be a data scientist, but you should be comfortable navigating technical tools,
Course Summaries
Build practical skills in implementing basic AI tools for spam filtering, anti-phishing, and biometric authentication—and again a solid understanding of how supervised and unsupervised learning approaches can serve as force multipliers in cybersecurity operations.
You’ll build:
- Perceptron-Based Spam Filter for SMS Data: Your first end-to-end ML tool
- Support Vector Machine for Spam Detection: Level up with “suspect” and “neutral” words, finding threats simpler models would miss
- Phishing Website Classifier with “One-Hot” Encoding: What’s best for the task? Linear regression, logic regression, or decision trees
- Biometric Keystroke Authentication System: Compare multiple models on a dataset of 51 user keystroke dynamics
- Biometric Facial Recognition for Secure ID: Using Principal Component Analysis and eigenfaces, you’ll implement dimensionality reduction techniques with the “Labeled Faces in the Wild” dataset for secure identity verification.
Create advanced systems that ID signature-based methods miss. You’ll develop sophisticated solutions for malware analysis for PE file examination, botnet detection, and industrial control system protection.
Then explore Hidden Markov Models for identifying self-modifying malware, K-means clustering for malware classification, and self-healing capabilities
By course completion, you’ll possess a toolkit of AI-powered security implementations—including models for self-modifying malware detection, pattern recognition for unknown threats, and transparent AI for network anomaly detection. These skills enable you to implement adaptive security solutions that don’t rely solely on known signatures, significantly strengthening your defense capabilities.
You’ll build:
- Static Malware Feature Extractor: Use PEview to extract features from Windows executables for ML analysis.
- Decision Tree Malware Classifier: Train a decision tree to classify executables using labeled malware data.
- Malware Clustering with K-Means: Build a K-means model to group files as malware or benign based on PE headers.
- Statistical Anomaly Detector: A simple Python system to flag unusual network behavior using thresholds.
- Botnet Detector with Supervised Learning: Use KNN, decision tree, and Naive Bayes to detect botnet traffic.
- Autonomic Cybersecurity System Prototype: A simulated IDS using multiple ML models to detect and explain attacks
Cybercriminals are using AI-based tools to outwit defenses. Analysts must adapt.
After breaking down a real-world use case of using IBM Watson to detect credit card fraud through advanced sampling techniques and ensemble models, Dr. Watkins takes you into the AI vs. AI domain.
You’ll learn how adversarial examples can compromise neural networks with “patch attacks,” how GANs evade detection systems, and how reinforcement learning agents methodically bypass security controls while preserving malicious functionality.
Then neutralize them with statistical anomaly detection, gradient masking, and adversarial training. Craft robust AI security systems capable of withstanding even the most advanced machine learning-based threats.
The course concludes with a critical analysis of H.S. Anderson’s Black Hat-presented RL malware-evasion framework.
You’ll build:
- Credit Card Fraud Prevention System with IBM Watson: Compare Random Forest and Extreme Gradient Boosting algorithms.
- GAN Handwriting Implementation: See for yourself the competition between the generator and discriminator networks.
- Maze Reinforcement Learning Agent: Use Q-learning algorithms to allow the agent to learn optimal pathways and maximize rewards.
- Statistical Anomaly Detector: A simple Python system to flag unusual network behavior using thresholds.
- Botnet Detector with Supervised Learning: Use KNN, decision tree, and Naive Bayes to detect botnet traffic.
- Autonomic Cybersecurity System Prototype: A simulated IDS using multiple ML models to detect and explain attacks
Tab 4 content.
Course Delivery and Support
The courses are delivered entirely online through the industry-leading Canvas Learning Management System. This system is supported by the same instructional design team behind Johns Hopkins’ renowned Engineering for Professionals program, which serves thousands of online graduate students each year. Upon registration, you will receive an email with instructions to create your Hopkins Canvas account and access the videos, readings, files and quizzes.
Certificate in AI for Cybersecurity
Cybersecurity
Online Self-Paced
60 hours
6 CEUs
$1500
$1200
No Risk: Explore the Certificate for 7 Days