20 citations · 123 across the 14 of their papers we have counts for
15 papers
Bandit Sequential Posted Pricing via Half-Concavity
Sahil Singla, Yifan Wang
Sequential posted pricing auctions are popular because of their simplicity in practice and their tractability in theory. A usual assumption in their study is that the Bayesian prio…
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
Mazda Moayeri, Wenxiao Wang, Sahil Singla +1
We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model traini…
Improved techniques for deterministic l2 robustness
Sahil Singla, Soheil Feizi
Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the norm is useful for adversarial robustness, interpretable gradients and stable t…
Core Risk Minimization using Salient ImageNet
Sahil Singla, Mazda Moayeri, Soheil Feizi
Deep neural networks can be unreliable in the real world especially when they heavily use spurious features for their predictions. Recently, Singla & Feizi (2022) introduced the Sa…
Salient ImageNet: How to discover spurious features in Deep Learning?
Sahil Singla, Soheil Feizi
Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we defin…
Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
Sahil Singla, Surbhi Singla, Soheil Feizi
Training convolutional neural networks (CNNs) with a strict Lipschitz constraint under the norm is useful for provable adversarial robustness, interpretable gradients and s…
Skew Orthogonal Convolutions
Sahil Singla, Soheil Feizi
Training convolutional neural networks with a Lipschitz constraint under the norm is useful for provable adversarial robustness, interpretable gradients, stable training, e…
Understanding Failures of Deep Networks via Robust Feature Extraction
Sahil Singla, Besmira Nushi, Shital Shah +2
Traditional evaluation metrics for learned models that report aggregate scores over a test set are insufficient for surfacing important and informative patterns of failure over fea…
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models
Cassidy Laidlaw, Sahil Singla, Soheil Feizi
A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the very definition of adversarial attacks that are im…
Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
Vedant Nanda, Samuel Dooley, Sahil Singla +2
Deep neural networks (DNNs) are increasingly used in real-world applications (e.g. facial recognition). This has resulted in concerns about the fairness of decisions made by these…
Second-Order Provable Defenses against Adversarial Attacks
Sahil Singla, Soheil Feizi
A robustness certificate is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For {\it any} input perturbations with a magnitud…
Fantastic Four: Differentiable Bounds on Singular Values of Convolution Layers
Sahil Singla, Soheil Feizi
In deep neural networks, the spectral norm of the Jacobian of a layer bounds the factor by which the norm of a signal changes during forward/backward propagation. Spectral norm reg…
Certifiably Robust Interpretation in Deep Learning
Alexander Levine, Sahil Singla, Soheil Feizi
Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensi…
Robustness Certificates Against Adversarial Examples for ReLU Networks
Sahil Singla, Soheil Feizi
While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. D…
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Sahil Singla, Eric Wallace, Shi Feng +1
Current methods to interpret deep learning models by generating saliency maps generally rely on two key assumptions. First, they use first-order approximations of the loss function…