Sahil Singla

Atoosa Malemir Chegini

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

2023

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Reliable Deep Learning: a Robustness Perspective.

[BibT_eX]

[DOI]

PhD thesis, 2022

Spuriosity Rankings: Sorting Data for Spurious Correlation Robustness.

[BibT_eX]

[DOI]

CoRR, 2022

Data-Centric Debugging: mitigating model failures via targeted data collection.

[BibT_eX]

[DOI]

Atoosa Malemir Chegini

CoRR, 2022

Core Risk Minimization using Salient ImageNet.

[BibT_eX]

[DOI]

CoRR, 2022

Hard ImageNet: Segmentations for Objects with Strong Spurious Cues.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Improved techniques for deterministic l2 robustness.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100.

[BibT_eX]

[DOI]

Surbhi Singla

Proceedings of the Tenth International Conference on Learning Representations, 2022

Salient ImageNet: How to discover spurious features in Deep Learning?

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Causal ImageNet: How to discover spurious features in Deep Learning?

[BibT_eX]

[DOI]

CoRR, 2021

Householder Activations for Provable Robustness against Adversarial Attacks.

[BibT_eX]

[DOI]

Surbhi Singla

CoRR, 2021

Skew Orthogonal Convolutions.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models.

[BibT_eX]

[DOI]

Cassidy Laidlaw

Proceedings of the 9th International Conference on Learning Representations, 2021

Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Low Curvature Activations Reduce Overfitting in Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the FAccT '21: 2021 ACM Conference on Fairness, 2021

Understanding Failures of Deep Networks via Robust Feature Extraction.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020

Second-Order Provable Defenses against Adversarial Attacks.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Bounding Singular Values of Convolution Layers.

[BibT_eX]

[DOI]

CoRR, 2019

Certifiably Robust Interpretation in Deep Learning.

[BibT_eX]

[DOI]

Alexander Levine

CoRR, 2019

Robustness Certificates Against Adversarial Examples for ReLU Networks.

[BibT_eX]

[DOI]