CRADLE Lab members contribute to undergraduate and graduate courses in cybersecurity, AI, and computer science at the University of Michigan-Flint.
DSC 525 — Big Data Analytics
Study of techniques and tools for extracting knowledge from massive amounts of data. Introduction to fundamental concepts in big data and machine learning methods required for handling large-scale data science problems; systems and techniques to store large volumes of data and analyze them using cluster/cloud computing based on map-reduce frameworks such as Hadoop MapReduce; and cloud computing tools such as Amazon AWS, Google Cloud or Microsoft Azure for big data mining tasks.
DSC 511 — Advanced Data Mining Algorithms and Applications
Study of the extraction of useful patterns from raw data using statistical techniques and machine learning methods. Topics include fundamental steps for exploratory data analysis including data pre-processing and visualization, dimension reduction and data transformation, and a variety of supervised and unsupervised machine learning methods such as classification, prediction and cluster analysis. Students gain hands-on experience by implementing methods covered on various platforms.
DSC 502 — Data Visualization for Exploratory Data Analysis
Study of visualization methods using a wide range of tools, from scripting languages to off-the-shelf software packages, and select topics in data science and machine learning. Overview of design and information literacy; ethical aspects of visualization; fundamental data manipulation techniques such as data preprocessing and dimension reduction; challenges in temporal, geo-spatial and network data visualization using appropriate tools.
DSC 528 — Deep Learning
Study of fundamental principles, mathematical foundations, and implementations of deep learning. Topics include methods such as gradient descent and backpropagation used to optimize models; model types such as linear, pooling and convolutional layers; and common neural network architectures, with applications from computer vision to natural language processing.
CYB 101 — Security Fundamentals I
Introduction to cybersecurity and the challenges of designing and implementing secured systems. Topics include the characterization of cyber roles for cohesive security systems, the Security Operation Center (SOC) mission, the fundamentals of networking, and an in-depth exploration of the open systems interconnection (OSI) model layers and common protocols. Focus on fundamental technical security skills for building secured networks, including OSI model security, control strategies, and authentication options. The basics of Unix/Linux are introduced to enable hands-on projects. Course uses experiential learning environments.
CYB 303 — Security Operations
Fundamentals of cybersecurity related to business operations and concepts required to recognize attacks against enterprise networks, including mission-critical business applications, Development Security Operations (DevSecOps), Security Orchestration and Response (SOAR), and Security Operation Center (SOC). Includes discussions of security breach cost, asset identification risk management, and cyber law associated with managing enterprise networks.
CYB 440 — Data Science for Cybersecurity
Investigation of data science approaches such as intrusion detection, malware classification, and network analysis used to mitigate cybersecurity problems. Exploration of supervised and unsupervised machine learning techniques aimed toward maintainable, reliable and scalable data mining systems in the security space. Introduction to adversarial machine learning through real world problems and datasets.
CYB 540 — Algorithmic Machine Learning for Cybersecurity
Investigation of data science approaches such as intrusion detection, malware classification, and network analysis used to mitigate cybersecurity problems. Exploration of supervised and unsupervised machine learning techniques aimed toward maintainable, reliable and scalable data mining systems in the security space. Introduction to adversarial machine learning through real world problems and datasets.
CSC 335 — Computer Networks I
Theoretical concepts necessary to understand the complex problem of computer networking. Computer network architectures and models, bandwidth limitations of physical media, analog and digital signaling methods, data link protocols, error detection and correction, medium access control in broadcast networks, routing algorithms, internetworking, the Internet Protocol, connection management, transport services including TCP/UDP, network applications, local-area and wide-area networks.
CSC 535 — Advanced Computer Networking
Advanced topics in computer networking. May include layered network architecture, transmission techniques on wired and wireless mediums, transmission impairments, bandwidth limitations, signaling techniques, error correction and detection, transmission protocols, contention-based medium access protocols, queuing theory, routing algorithms, internetworking, connection management, performance issues, application-level protocol standards, communication of multimedia over computer networks.