3 credits
Fall 2025 Lecture Upper Division
This course focuses on applied data mining, machine learning, data analytics techniques, and their application and relevance in information security. The course covers basic concepts of data mining and machine learning, computation platforms in support of big data analytics including Map-Reduce and Spark, machine learning algorithms such as classification trees, logistic regression, naive Bayes, k Nearest Neighbors, Support Vector Machines, Artificial Neural Networks (including Feed Forward, Convolutional, and Recurrence), the application of these algorithms to security tasks such as Spam/Phishing detection, malware detection, intrusion detection, and situational awareness. The future and potential role of applying machine learning techniques in information and data security is explored.
Learning Outcomes1Explain commonly used machine learning algorithms relevant to information security; identity their strengths and weaknesses and illustrate their relevance through examples.
2Identify security problems that can be solved by using machine learning (including deep learning) techniques.
3Explain the concepts of artificial neural networks, including feed forward networks, convolutional neural networks, and recurrent neural networks.
4Deploy machine learning algorithms (including artificial neural networks) using software such as NumPy, SciPy, and TensorFlow.
5Apply Spark and HDFS to perform data analysis.
6Apply machine learning algorithms to security problems.
7Assess the effectiveness of applying data analytics techniques to different security problems and explain existing shortcomings of ML techniques.
8Explain what type of data visualization can be effective for security problems (e.g., in fraud detection).
9Explain the concept of adversarial machine learning and the common attacks/defenses.
Prerequisites
Restrictions
made by Purdue students.