ECE 69500 - Big Data for Reliability and Security
Course Details
Lecture Hours: 1 Credits: 1
Areas of Specialization:
- Communications, Networking, Signal & Image Processing
- Computer Engineering
Counts as:
Normally Offered:
Each Fall
Campus/Online:
On-campus and online
Requisites by Topic:
Python programming; basic knowledge of probability and statistics.
Catalog Description:
This course briefly covers the theoretical aspects of big data for reliability and security and stresses the practical systems aspects of such techniques. There are two challenge programming problems based on large real-world datasets that we have collected and curated.
Required Text(s):
None.
Recommended Text(s):
None.
Learning Outcomes
- Formulate the reliability and the security requirements of a production system.
- Understand and develop big data techniques for improving reliability and security of computing systems.
- Construct software artifacts to instantiate the techniques for real-world datasets and under realistic conditions.
Lecture Outline:
| Lectures | Lectures |
|---|---|
| 2 | Foundational material on reliability and security: reliability and security landscape for connected systems |
| 5 | Data analytic techniques for dependability: supervised and unsupervised learning; neural network building blocks; regularization, feature engineering, dimensionality reduction, etc. |
| 5 | Big data security and insecurity: evasion and poisoning attacks; white and black box attacks; defenses; federated learning |
| 3 | Case studies and challenge problems |
Assessment Method:
Class participation, quizzes, programming assignments, final exam. (3/2022)