8 citations · 10 across the 6 of their papers we have counts for
5 papers · 1 filter
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
Rongzhe Wei, Mufei Li, Mohsen Ghassemi +7
Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its r…
Auditing and Enforcing Conditional Fairness via Optimal Transport
Mohsen Ghassemi, Alan Mishler, Niccolo Dalmasso +4
Conditional demographic parity (CDP) is a measure of the demographic parity of a predictive model or decision process when conditioning on an additional feature or set of features.…
Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls
Aras Selvi, Eleonora Kreacic, Mohsen Ghassemi +3
Adversarially robust optimization (ARO) has emerged as the *de facto* standard for training models that hedge against adversarial attacks in the test stage. While these models are…
Guarding Multiple Secrets: Enhanced Summary Statistic Privacy for Data Sharing
Shuaiqi Wang, Rongzhe Wei, Mohsen Ghassemi +2
Data sharing enables critical advances in many research areas and business applications, but it may lead to inadvertent disclosure of sensitive summary statistics (e.g., means or q…
Synthetic Data Applications in Finance
Vamsi K. Potluru, Daniel Borrajo, Andrea Coletta +17
Synthetic data has made tremendous strides in various commercial settings including finance, healthcare, and virtual reality. We present a broad overview of prototypical applicatio…