Trustworthy Machine Learning

List curated by Reza Shokri (National University of Singapore) and Nicolas Papernot (University of Toronto and Vector Institute)

Machine learning algorithms are trained on potentially sensitive data, and are increasingly being used in critical decision making processes. Can we trust machine learning frameworks to have access to personal data? Can we trust the models not to reveal personal information or sensitive decision rules? In the settings where training data is noisy or adversarially crafted, can we trust the algorithms to learn robust decision rules? Can we trust them to make correct predictions on adversarial or noisy data? Bias affecting some groups in the population underlying a dataset can arise from both a lack of representation in data but also poor choices of learning algorithms. Can we build trustworthy algorithms that remove disparities and provide fair predictions for all groups? To identify various issues with machine learning algorithms and establish trust, can we provide informative interpretation of machine learning decisions? These are the major questions that the emerging research field of trustworthy machine learning aims to respond.

We have selected different sub-topics and key related research papers (as starting points) to help a student learn about this research area. There are so many good papers which are being published in this domain. This list is by no means comprehensive. Papers are selected here with the intention of maximizing coverage of the techniques introduced in the literature in as few papers as possible. Students are encouraged to dive deeper by reading the follow-up research papers.

Privacy and Confidentiality

Data Inference Attacks

Memorization

Model Inference Attacks

Privacy-Preserving Learning

Confidential Computing

Machine Unlearning

Decentralized (Collaborative, Federated) Learning

Law and Policy

Tools and Libraries

Robustness

Training Phase

Inference Phase - adversarial examples against integrity

Inference Phase - hardware attacks on availability

Testing and Verification

Tools and Libraries

Law and Policy

Algorithmic Fairness

Measures

Mechanisms

Analysis

Robustness

Tools and libraries

Algorithmic Transparency

Model Explanation

Interpretability

Recourse

Robustness

Privacy and Confidentiality

Analysis

Law and Policy