3 papers
cs.LG2026
Certification-Based Differentially Private Learning
Mihnea Ghitu, Matthew Wicker
Differential privacy (DP) in machine learning is typically achieved by adding noise to model parameters (private learning) or to model outputs (private prediction). Recent work use…
cs.LG2026
Towards Poisoning Robustness Certification for Natural Language Generation
Mihnea Ghitu, Matthew Wicker
Understanding the reliability of natural language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide p…
cs.LG2025
Model Guidance via Robust Feature Attribution
Mihnea Ghitu, Vihari Piratla, Matthew Wicker
Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut featur…