Sotabase

Career

· ETH

Publications (48)

A User's Guide to the Encyclopedia of DNA Elements (ENCODE)
PLoS Biology · 2011
1,069
cited
Calibrating Deep Neural Networks using Focal Loss
Neural Information Processing Systems · 2020
576
cited
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
International Conference on Machine Learning · 2018
131
cited
Progressive Skeletonization: Trimming more fat from a network at initialization
International Conference on Learning Representations · 2020
108
cited
Towards Adversarial Evaluations for Inexact Machine Unlearning
2022
78
cited
How benign is benign overfitting?
International Conference on Learning Representations · 2020
61
cited
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Neural Information Processing Systems · 2022
58
cited
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
International Conference on Learning Representations · 2019
54
cited
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Neural Information Processing Systems · 2024
44
cited
Open Problems in Machine Unlearning for AI Safety
arXiv.org · 2025
41
cited
How robust is unsupervised representation learning to distribution shift?
International Conference on Learning Representations · 2022
31
cited
Optimizing non-decomposable measures with deep networks
Machine-mediated learning · 2018
28
cited
How unfair is private learning ?
Conference on Uncertainty in Artificial Intelligence · 2022
26
cited
Corrective Machine Unlearning
Trans. Mach. Learn. Res. · 2024
21
cited
How robust are pre-trained models to distribution shift?
arXiv.org · 2022
18
cited
Robustness via Deep Low-Rank Representations
2018
18
cited
PILLAR: How to make semi-private learning more effective
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · 2023
14
cited
A law of adversarial risk, interpolation, and label noise
International Conference on Learning Representations · 2022
10
cited
Multiscale sequence modeling with a learned dictionary
arXiv.org · 2017
10
cited
Differentially Private Steering for Large Language Model Alignment
International Conference on Learning Representations · 2025
8
cited
Sotabase