There are more examples of principled approaches to analyzing machine learning security in our work. We applied quantitative verification for fairness and adversarial robustness for neural networks. We have analyzed when membership inference tests are conclusive. Our work shows the importance of causal reasoning here, as opposed to drawing conclusions purely with observations of statistical correlation. We have worked on making differential privacy more practical for fully-distributed graph processing, e.g. for hierarchical clustering and training GNNs. Lastly, we are studying data repudiation, i.e., convincing a verifier that a data point was not used in training.