Fanny Yang

How robust accuracy suffers from certified training with convex relaxations

2023 · arXiv (Cornell University)

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified defences come with robustness guarantees, empirical …

Copyright-Protected Language Generation via Adaptive Model Fusion

2024 · arXiv (Cornell University)

The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown promise in addressing …