top of page

Course Description

Step into the forefront of cyber warfare with the Boston Cybernetics Institute's "Data Science for Strategic Cyber Operations" course. This advanced 60-day program is meticulously tailored for seasoned cybersecurity professionals who are looking to leverage data science in the pursuit of operational excellence in computer network operations (CNO).

Integrating machine learning theory with the practicalities of data preprocessing, our course is designed to elevate your understanding of how to transform data into actionable intelligence. You'll explore advanced techniques in data analysis and visualization, drawing upon probability and information theory to extract and interpret complex cyber patterns. With a strong underpinning in statistics, you will refine your ability to make data-driven decisions in the context of national security and corporate defense.

Our curriculum delves into the strategic applications of supervised and reinforcement learning, optimization, and deep learning, with a specific focus on their roles in developing robust cyber defense mechanisms. Transfer learning is highlighted as a pivotal skill for adapting existing models to new threats, ensuring your capabilities remain cutting-edge in an evolving threat landscape.

We prioritize operational effectiveness, suitability, and survivability, with exercises modeled on real-world scenarios that demand innovative solutions. This hands-on course facilitates your mastery of data science metrics and techniques, graph theory, and network science, all essential tools for disrupting and decoding adversarial communications.

As cyber operations become increasingly sophisticated, the inclusion of natural language processing (NLP) empowers you to counteract and exploit enemy propaganda, deciphering hidden messages and intents. This program not only hones your technical skills but also prepares you for the psychological aspects of cyber warfare.

The course is an investment in strategic advantage, whether for US military applications or for fortifying private sector networks against state-level adversaries. As a participant, you will benefit from the Boston Cybernetics Institute's unparalleled teaching methodology, simulating the high-pressure environment of cyber operations and fostering a deep, intuitive understanding of data science as a critical tool in the cybersecurity arsenal.

Join us to transform your cyber capabilities and become a vanguard of digital defense, where data is not just a resource but a weapon sharpened by the finest minds in the field.

Curriculum Overview: Detailed Course Breakdown

Machine Learning Theory

Under the domain of Machine Learning Theory, this course delves into the foundational principles and algorithms that enable machines to make data-driven predictions and decisions. Students will explore how these principles apply to cyber operations, particularly in identifying patterns and anomalies within massive data sets that could indicate security breaches. Emphasis will be placed on understanding the underlying mechanics of various algorithms to tailor them for robust and secure applications in a cyber context.

Data Preprocessing

Data Preprocessing is a critical step in the machine learning pipeline, especially within the realm of cybersecurity. Students will learn techniques for cleaning, normalizing, and encoding data, transforming raw data into a format that machine learning algorithms can exploit effectively. The course will cover how preprocessing can affect the performance of cybersecurity models and the importance of preprocessing in ensuring that the data does not contain biases or vulnerabilities that adversaries could exploit.

Data Analysis and Visualization

In this section, we cover tools and techniques for analyzing and visualizing complex datasets. This will enable students to uncover hidden patterns, correlations, and insights that can inform cybersecurity strategies. Visualization skills are crucial for communicating findings to both technical and non-technical stakeholders, facilitating the swift decision-making necessary in responding to cyber threats.

Probability and Information Theory

Probability and Information Theory provide the mathematical underpinnings for making sense of uncertain events and quantifying information within data. From a cybersecurity perspective, these topics are instrumental in modeling risks, evaluating system entropies, and developing cryptographic algorithms. Students will learn to apply these theories to enhance the security and reliability of data transmission and storage.


Statistics forms the backbone of making informed decisions based on data. This course will teach statistical methods and their applications in cybersecurity, such as for intrusion detection systems (IDS) and network traffic analysis. Students will gain expertise in hypothesis testing, regression analysis, and statistical significance, equipping them to discern and react to statistical anomalies in security data.

Supervised Learning

In the realm of Supervised Learning, students will focus on building and deploying models that can classify and predict outcomes based on labeled data. Cybersecurity applications include spam detection, phishing email identification, and malware classification. The course will stress the importance of feature selection, model complexity, and training strategies to avoid overfitting and ensure generalizability to unseen data.

Reinforcement Learning

Reinforcement Learning (RL) is an area of machine learning concerned with how software agents ought to take actions in an environment to maximize some notion of cumulative reward. In cybersecurity, RL can be applied to develop autonomous systems for threat detection and response. The course will cover RL algorithms and how to apply them in scenarios where security environments are continuously changing and where the system must adapt to maintain robust defenses.


Optimization is critical in machine learning and cybersecurity for improving the performance of algorithms and systems. Students will learn optimization techniques that are essential for fine-tuning machine learning models, including those used in predictive analytics for cyber threat intelligence. The course emphasizes the balance between computational efficiency and the precision of outcomes, especially in resource-constrained scenarios.

Deep Learning

Deep Learning is an advanced subset of machine learning that uses layered neural networks. It has significant implications for cybersecurity, such as in behavior analysis to detect anomalies and in the creation of systems that can identify sophisticated threats. The course will cover the architecture of deep neural networks, training strategies, and the deployment of these models in secure environments.

Transfer Learning

Transfer Learning allows a model developed for one task to be reused as the starting point for another task. This course section will explore how transfer learning can expedite the development of cybersecurity models by leveraging pre-trained networks. It addresses the challenges of data scarcity in the cyber domain and how transfer learning can provide a head start in detecting advanced persistent threats (APTs).

Data Science Metrics/Techniques

Data Science Metrics/Techniques are essential for evaluating the performance of cybersecurity models. This course will cover a range of metrics, such as precision, recall, and the ROC curve, that are used to measure the effectiveness of machine learning models in detecting and responding to cyber incidents. Techniques such as cross-validation and bootstrapping will be discussed to estimate the performance of models in a robust manner.

Graph Theory/Network Science

Graph Theory and Network Science are instrumental in understanding and visualizing the structure and dynamics of networks, which are central to cybersecurity. Students will learn to apply these mathematical tools to model network traffic, detect community structures in social engineering attacks, and analyze the robustness of networks against attacks. The course will highlight the use of graph algorithms in identifying vulnerabilities and securing network infrastructures.

Natural Language Processing (NLP)

Natural Language Processing (NLP) is leveraged in cybersecurity for analyzing textual data and extracting meaningful information. This could include automating the monitoring of dark web forums for threat intelligence or detecting phishing attempts in emails. The course will cover various NLP techniques, from tokenization to sentiment analysis, and their cybersecurity applications, including the automated generation of cyber threat reports and the understanding of hacker communications.

Who Should Take This Course?

This course is designed for individuals who are passionate about the intersection of cybersecurity and data science. It is particularly well-suited for:

  • Cybersecurity Professionals looking to enhance their analytical skills and apply machine learning to secure digital infrastructures.

  • Data Scientists and Analysts aiming to specialize in security-related data challenges and threat intelligence.

  • Computer Science Students and Researchers interested in the cutting-edge applications of AI in cybersecurity.

  • IT Professionals who wish to upskill in the rapidly growing field of cyber analytics to anticipate and mitigate cyber threats.

  • Policy Makers and Security Consultants needing a deeper technical understanding of machine learning applications in cybersecurity to inform strategy and decision-making.

  • Machine Learning Enthusiasts and Hobbyists with a specific interest in the security domain and the ethical implications of AI.

The course material is rigorous and assumes a basic understanding of programming, statistics, and machine learning concepts. It is tailored for those who are committed to deepening their expertise and are seeking practical, in-depth knowledge to apply in real-world cybersecurity scenarios.

About Boston Cybernetics Institute

Boston Cybernetics Institute, PBC was created by former MIT Lincoln Lab cybersecurity researchers to give meaningful niche cyber instruction to a new generation of cybersecurity professionals.


We avoid the normal style of teaching with PowerPoint and lectures, opting to provide instead real-life engaging instruction that takes place in a customized environment. We have given our style of instruction to multiple DoD agencies, US commercial companies, and international companies.


Instructors at Boston Cybernetics Institute

Jeremy Blackthorne.png

Jeremy Blackthorne

President of the Boston Cybernetics Institute

Jeremy Blackthorne is a Lead Instructor at the Boston Cybernetics Institute (BCI). Before BCI, he was a researcher in the Cyber System Assessments group at MIT Lincoln Laboratory. Blackthorne is the co-creator and instructor for the Rensselaer Polytechnic Institute (RPI) courses: Modern Binary Exploitation, Spring 2015 and Malware Analysis, Spring 2013. ​Jeremy has published research at various academic and industry conferences. He served in the U.S. Marine Corps and is an alumnus of RPISEC. He holds a BS and MS in computer science. ​ Blackthorne was an active member of the Student Security Club and CTF team, RPISEC, from 2012 to 2015, where he taught seminars on Reverse-Engineering, Exploitation, and various other Cybersecurity topics.


Clark Wood

security researcher and instructor

Clark Wood is a security researcher and instructor at the Boston Cybernetics Institute (BCI), focusing on Reverse Engineering, Exploitation, and CI/CD. He recently built a Reverse-Engineering and Exploitation platform for a DoD customer and is the Lead Engineer for BCI’s Government Services. Clark was formerly on the technical staff at MIT Lincoln Laboratory where he was a member of the Cyber System Assessments Group. ​Clark holds a BA in Economics from the University of Florida, a BS and MS in Computer Science from Florida State University, and a Master’s in Technology and Policy from MIT. ​


Rodolfo Cuevas

security researcher and instructor

Rodolfo Cuevas is a security researcher and instructor at BCI, where he focuses on understanding how design constraints can be used to limit the impact of an attacker on a system. His research combines the adversarial mindset with approaches influenced by Systems and Control Theory. ​ Rodolfo was a staff member at MIT Lincoln Laboratory and began his career as a RADAR and Ballistic Missile Defense System (BMDS) analyst. Later, Rodolfo transitioned to evaluating and Red-Teaming tactical and commercial cyber systems in support of DoD and other government programs. ​ Rodolfo holds a BS, M.Eng., and M.S. in Electrical and Computer Engineering from Cornell University.


Reed Porada

security researcher and instructor

Reed Porada is a security researcher and instructor at BCI, focused on getting to the "so what" of both defensive and offensive cyber measures. Reed also leads BCI training in Cyber Systems Analysis, focusing on developing systems-thinking skills of developers up to managers. ​Reed was a staff member at MIT Lincoln Laboratory for ten years, where he was responsible for Test and Evaluation, Test Automation Research, Red-Teaming of Cyber Systems, and Blue System Architectures. Reed was a computer scientist at the Naval Research Laboratory focused on wireless communication systems. He holds a BS in Computer Science from the University of Maryland, College Park and an MS in Software Engineering from Carnegie Mellon University.

Senior CNO Developer Course: Data Science for Strategic Cyber Operations



Upon request


60 days

What happens after I click the button?

Your default e-mail client will pop up and you'll be asked to write us a short message. Please let us know which course you are interested in and what dates would work for you.

Anchor 1
bottom of page