research
∙
01/29/2023
Scaling in Depth: Unlocking Robustness Certification on ImageNet
Notwithstanding the promise of Lipschitz-based approaches to determinist...
share
research
∙
01/21/2023
Limitations of Piecewise Linearity for Efficient Robustness Certification
Certified defenses against small-norm adversarial examples have received...
research
∙
06/01/2022
On the Perils of Cascading Robust Classifiers
Ensembling certifiably robust neural networks has been shown to be a pro...
research
∙
11/16/2021
Selective Ensembles for Consistent Predictions
Recent work has shown that models trained to the same objective, and whi...
research
∙
07/23/2021
Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair
Neural networks are increasingly being deployed in contexts where safety...
research
∙
06/11/2021
Relaxing Local Robustness
Certifiable local robustness, which rigorously precludes small-norm adve...
research
∙
02/16/2021
Globally-Robust Neural Networks
The threat of adversarial examples has motivated work on training certif...
research
∙
05/03/2020
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
LSTM-based recurrent neural networks are the state-of-the-art for many n...
research
∙
02/12/2020
Fast Geometric Projections for Local Robustness Certification
Local robustness ensures that a model classifies all inputs within an ϵ-...
research
∙
06/27/2019
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
Membership inference (MI) attacks exploit a learned model's lack of gene...
research
∙
12/21/2018
Feature-Wise Bias Amplification
We study the phenomenon of bias amplification in classifiers, wherein a ...
research
∙
02/11/2018