top of page

Trustworthy Machine Learning
Spring 2022

Lecture 01
Introduction to trustworthy ML
Lecture 02
ML overview (common ML models, optimization, ML procedures, SGD)
Lecture 03
ML overview (practical aspects of ML, optimization techniques, NNs, back propagation, Pytorch)
Lecture 04
Attacks and adversaries, data inference attacks, membership inference, white-box attacks, information leakage
Lecture 05
Membership inference attacks against machine learning model
Arif Huzaifa
Lecture 06
Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning
Roman Vakhrushev
Lecture 07 (I)
Information Leakage in Embedding Models
Ryan Kaplan
Lecture 07 (II)
CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel
Alex Sidgwick
Lecture 08 (I)
Exploring connec- tions between active learning and model extraction
Anmol Dwivedi
Lecture 08 (II)
High Accuracy and High Fidelity Extraction of Neural Networks.
M. Shahid Modi
Lecture 09
Introduction to privacy, differential privacy, private distributed learning, privacy evaluation
Lecture 10
Deep learning with differential privacy
Momin Abbas
Lecture 11 (I)
Scalable private learning with PATE
Zehao Li
Lecture 11 (II)
Differentially private fair learning
Burak Varici
Lecture 12 (I)
On sampling, anonymization, and differential privacy or, k- anonymization meets differential privacy
Charlie Cook
Lecture 12 (II)
Evaluating differentially private machine learning in practice
Sharmishtha Dutta
Lecture 13
Robustness, robust training, certified defense, robust optimization, adversarial examples, black-box attacks
Lecture 14
Poisoning attacks against support vector machines
Arpan Mukherjee
Lecture 15
Manipulating machine learning: Poisoning attacks and countermeasures for regression learning
Dong Hu
Lecture 16
Explaining and harnessing adversarial examples
Vijay Sadashivaiah
Lecture 17 (I)
Practical black-box attacks against machine learning
Alex Mankowski
Lecture 17 (II)
A robust meta-algorithm for stochastic optimization
Bao Pham
Lecture 18
Mitigating unwanted biases with adversarial learning
Kara Davis
Lecture 19
Fairness, fairness measures, counterfactuals, fair representation, certified fairness, bias mitigation, fair classification
Lecture 20
Equality of opportunity in supervised learning
Matthew Youngbar
Lecture 21 (I)
Fairness through awareness
Farhad Mohsin
Lecture 21 (II)
Learning fair representations
Farhad Mohsin
Lecture 22 (I)
Counterfactual fairness
Rhea Banerjee
Lecture 22 (II)
Fairness constraints: Mechanisms for fair classification
Rhea Banerjee
Lecture 23
Transparency, explainability, trust, transparency, interpretability
Lecture 24 (I)
Towards a rigorous science of interpretable machine learning
Zirui Yan
Lecture 24 (II)
Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems
Zirui Yan
Lecture 25 (I)
A unified approach to interpreting model predictions
Lucky Yerimah
Lecture 25 (II)
Why should I trust you? Explaining the predictions of any classifier
Lucky Yerimah
Lecture 26
Explaining explanations in AI
Andrew Nguyen
bottom of page