20 citations · 51 across the 6 of their papers we have counts for
4 papers · 1 filter
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Liam Fowl, Jonas Geiping, Steven Reich +4
A central tenet of Federated learning (FL), which trains models without centralizing user data, is privacy. However, previous work has shown that the gradient updates used in FL ca…
Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast-Choose Three
Steven Reich, David Mueller, Nicholas Andrews
Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple…
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
Micah Goldblum, Steven Reich, Liam Fowl +3
Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods,…
WITCHcraft: Efficient PGD attacks with random step size
Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum +4
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods wit…