Marissa Connor

Learning Identity-Preserving Transformations on Data Manifolds

2021 · arXiv (Cornell University)

Many machine learning techniques incorporate identity-preserving transformations into their models to generalize their performance to previously unseen data. These transformations are typically selected from a set of functions that are known to maintain the identity …

Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning

2022 · arXiv (Cornell University)

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the unlabeled training samples, …