Course Schedule
CSCI 49395 - Fall 2026
Week 1 - Tuesday, August 25, 2026
Course Introduction: Trustworthy Big Data Systems
Week 1
Integrating Big Data, AI & Privacy
Course Overview
Week 2 - Tuesday, September 1, 2026
Privacy Fundamentals and PII
Week 2
Fundamental Privacy Concepts
Personally Identifiable Information (PII)
Privacy Risks at Scale
Release: A1 - Lab 1: Detecting PII in Large Datasets
Week 3 - Tuesday, September 8, 2026
Privacy Attacks and Data Anonymization
Week 3
Re-identification & Linkage Attacks
k-anonymity
l-diversity
Limitations of Anonymization
Release: A2 - Lab 2: Anonymization — k-anonymity & l-diversity
Due: A1 - Lab 1: Detecting PII in Large Datasets
Week 4 - Tuesday, September 15, 2026
Differential Privacy: Foundations and Applications
Week 4
DP Principles & Math Foundations
Rigorous Privacy Guarantees
Practical DP Applications
Release: A3 - Lab 3: Differential Privacy in Practice
Due: A2 - Lab 2: Anonymization — k-anonymity & l-diversity
Week 5 - Tuesday, September 22, 2026
Privacy Regulations and Compliance
Week 5
GDPR
CCPA
NYC AI Law
Compliance in Data-Driven Systems
Release: A9 - Problem Set 2: Differential Privacy & Regulations
Due: A8 - Problem Set 1: Privacy Foundations & Anonymization
Week 6 - Tuesday, September 29, 2026
Apache Spark and Big Data Pipelines
Week 6
Apache Spark
Scalable Data Processing
Privacy-Aware Pipelines
Release: A4 - Lab 4: Privacy-Preserving Pipelines with Apache Spark
Due: A3 - Lab 3: Differential Privacy in Practice
Week 7 - Tuesday, October 6, 2026
Streaming and NoSQL Systems
Week 7
Real-Time Data Processing
NoSQL Databases
Due: A9 - Problem Set 2: Differential Privacy & Regulations
Week 8 - Tuesday, October 13, 2026
Cloud Computing and Data Lakes
Week 8
Cloud-Based Data Processing
Data Lakes
Modern Architectures
Release: A5 - Lab 5: Streaming, NoSQL & Cloud Data Lakes
Due: A4 - Lab 4: Privacy-Preserving Pipelines with Apache Spark
Week 9 - Tuesday, October 20, 2026
Large Language Models and Privacy
Week 9
LLMs
Privacy Risks in Training, Deployment & Use
Release: A6 - Lab 6: LLM Privacy — Membership Inference
Week 10 - Tuesday, October 27, 2026
Distributed AI and Large-Scale Model Training
Week 10
Distributed Training
Scalability & Privacy Challenges
Due: A5 - Lab 5: Streaming, NoSQL & Cloud Data Lakes
Week 11 - Tuesday, November 3, 2026
Privacy-Preserving Machine Learning
Week 11
Attacks Against ML Models
Privacy-Preserving Training & Evaluation
Due: A6 - Lab 6: LLM Privacy — Membership Inference
Week 12 - Tuesday, November 10, 2026
Federated Learning and Decentralized AI
Week 12
Federated Learning
Collaborative Privacy-Preserving Learning
Release: A7 - Lab 7: Federated Learning
Week 13 - Tuesday, November 17, 2026
Privacy in Big Data Systems
Week 13
Privacy Across Pipelines, Storage & Serving Layers
System Architectures
Week 14 - Tuesday, November 24, 2026
Final Project Presentations and Course Wrap-Up
Week 14
Final Project Presentations
Integrating Big Data, AI & Privacy
Due: A7 - Lab 7: Federated Learning