Guía docente de International Cyberintelligence (MQ2/56/1/12)

Cyberintelligence. Applied Data Science. Machine Learning. Anomaly Detection. Adversarial Machine Learning.

 A good knowledge of fundamentals of cybersecurity is, of course, necessary.

In addition, it is highly convenient to have a thorough background on the security aspects of the essential components of computing: operating systems, applications, networking, hardware platforms (servers, desktop computers, laptops, mobile computing, IoT devices). 

Finally, a solid knowledge on the foundations of Data Science and Machine Learning as well as practical skills in their application.

If AI tools are used to develop the tasks included in this course, students must adopt an ethical and responsible approach to their use. The recommendations contained in the document "Recommendations for the Use of Artificial Intelligence in the UGR" should be followed.

• Students will know and understand the fundamentals of international cyberintelligence.
• Students will be able to use and apply common cyberintellligence data extraction tools.
• Students will be able to use and apply common machine learning techniques.
• Students will be able to design and deploy a pipeline for the analysis of cyberintelligence data.
• Students will be able to evaluate existing machine learning tools and techniques.

1. The cyberintelligence lifecyle
   • Basis concepts of cyberintelligence
   • Roles in cyberintelligence
   • Lifecycle
2. Sources of Intelligence:
   • Human Intelligence (HUMINT)
   • Open-source intelligence (SOCINT)
   • Signal intelligence (SIGINT)
   • Technical intelligence (TECHINT)
   • Social media intelligence (SOCMINT)
3. Data Science for cyberIntelligence
   • Data integration
   • Data extraction
   • Data cleaning and preprocessing
   • Predictive modelling and pattern recognition
   • Supervised machine learning methods
   • Unsupervised machine learning methods
   • Anomaly detection methods
   • Adversarial machine learning
4. Applications in cyberintelligence
   • Social network analysis
   • Community detection methods

1. Data Science for Cyberintelligence
   1. Data location and extraction
   2. Data preprocessing and exploratory analysis
   3. Predictive modeling
   4. Anomaly detection
2. Solving real problems in cyberintelligence

• Pang-Ning Tan, Michael Steinbach, Anuj Karpatne & Vipin Kumar, 2019, "Introduction to Data Mining", ISBN 0273769227
• Mark E.J. Newman, 2018, "Networks: An Introduction", ISBN 0198805098
• Ian Goodfellow, Yoshua Bengio & Aaron Courville, 2016, "Deep Learning", ISBN 0262035618
• AnHai Doan, Alon Halevy & Zachary Ives, 2012, "Principles of Data Integration", ISBN 0124160441
• ChengXiang Zhai & Sean Massung, 2016, "Text Data Management and Analysis", ISBN 1970001194

• N. Heard, N. Adams, P. Rubin-Delanchy, M. Turcotte (eds), 2018, "Data Science for Cyber-Security", World Scientific
• I.H. Sarker, A.S.M. Kayes, S. Badsha, H. Alqahtani, P. Watters, A. Ng, "Cybersecurity data science: an overview from machine learning perspective", J. Big Data, 7, 41(2020), https://doi.org/10.1186/s40537-020-00318-5
• G. Dimitrov, "A Brief History of Cyber Intelligence", American Intelligence Journal, 37, 1 (2020) pp. 107-114. https://www.jstor.org/stable/27087688

• SnapperML 
• Python
• Orange Data Mining
• "Data Science for Cyber Security"
• "Use Data Science in Cybersecurity" 

For the regular exam, students must complete assignments given in class, give presentations and solve practical problems. This part accounts for 50% of the grade.

In addition, students must pass written exams, that account for 40%. A minimum of 15% (out the 40%) is necessary in this part for the student to be eligible to pass all the course.

Finally, attendance is valued up to a 10% fo the grade.

The student will have to pass a written exam on the theoretical and practical content of the course, which will take place in a single academic act.

The student will have to pass a written exam on the theoretical and practical content of the course, which will take place in a single academic act.

The contents of the course will be managed in the Arqus Virtual Campus (https://virtualcampus.arqus-alliance.eu)

Información de interés para estudiantado con discapacidad y/o Necesidades Específicas de Apoyo Educativo (NEAE): Gestión de servicios y apoyos (https://ve.ugr.es/servicios/atencion-social/estudiantes-con-discapacidad).

• Python
• Python Packages: PyPI
• Linux
• Orange Data Mining
• SnapperML