Cybersecurity Science with Shawn Riley

The cybersecurity industry, like many other sectors, is awash with data. From enterprise security controls and sensors to open source cybersecurity data, the volume of information is vast. Yet, the industry has been slow to adopt the FAIR data principles, a set of guidelines aimed at improving the Findability, Accessibility, Interoperability, and Reuse of digital assets. This article explores the FAIR data principles, their potential benefits to cybersecurity, the key enabling technologies for their implementation, and the impact of not implementing them in the cybersecurity industry. Understanding the FAIR Data Principles The FAIR data principles were established to enhance the utility and value of data assets. The acronym FAIR stands for Findable, Accessible, Interoperable, and Reusable, each representing a specific aspect of data management: Findable : Data and metadata should be easy to find for both humans and computers. They should be assigned a globally unique and persistent ide...

Today's experiment with ChatGPT4 was seeing how well it could support a creating a SKOS taxonomy from text I copy and pasted out of one of my Cybersecurity Science blogs, " A Standardized Vocabulary for Evaluating the Impact of Cyber Defense Decisions on Adversary Behavior " which contains an effects vocabulary from NIST 800-160 Vol 2 Rev 1 dated December 2021.  SKOS (Simple Knowledge Organization System) is a widely-used standard for representing knowledge organization systems, such as taxonomies, thesauri, and classification schemes. Here are some of the benefits of using SKOS: Interoperability : SKOS is a widely recognized and adopted standard, making it easy to share and exchange knowledge organization systems across different applications and platforms. This can improve interoperability and facilitate data integration and reuse. Consistency : SKOS provides a consistent way to represent knowledge organization systems, making it easier to manage and maintain them. This...

Artificial intelligence (AI) has been touted as the solution to a wide range of problems, from fraud detection to healthcare. However, the reality is that AI is not a silver bullet, and not all AI approaches are equal. One of the key limitations of machine learning, which has been the dominant AI approach in recent years, is that it can only operate on data that is already labeled or annotated. This means that machine learning algorithms can only detect patterns and associations that are already known. To go beyond this, AI needs to incorporate knowledge representation and reasoning to enable it to reason about the world and draw conclusions based on that reasoning. Machine learning has been the dominant AI approach in recent years, and it has been used to great effect in a wide range of applications. However, its limitations are becoming increasingly apparent. One of the key limitations of machine learning is that it requires labeled data to learn from. This means that machine learnin...

I. Introduction A. Background on Integrated Adaptive Cyber Defense (IACD) The rapid advancement of technology and the increasing interconnectedness of digital systems have led to an ever-increasing threat of cyber attacks. As the complexity and frequency of these attacks continue to rise, traditional cyber defense methods have proven to be insufficient. To address these challenges, a new approach to cybersecurity has emerged: Integrated Adaptive Cyber Defense (IACD). IACD is a holistic approach to cybersecurity that emphasizes an integrated and adaptive response to cyber threats. It combines advanced technologies, such as artificial intelligence and automation, with human expertise to create a dynamic defense system. IACD is designed to be adaptable and flexible, allowing it to respond to the evolving threat landscape and provide effective protection against a wide range of cyber attacks. B. Importance of IACD in today's cyber threat landscape The current cyber threat landscape is ...