163 citations · 1.4k across the 139 of their papers we have counts for
16 papers · 2 filters
Playing it Safe: Adversarial Robustness with an Abstain Option
Cassidy Laidlaw, Soheil Feizi
We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples. Adversarial examples ar…
Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation
Alexander Levine, Soheil Feizi
Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smo…
Adversarial Robustness of Flow-Based Generative Models
Phillip Pope, Yogesh Balaji, Soheil Feizi
Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application d…
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…
On Second-Order Group Influence Functions for Black-Box Predictions
Samyadeep Basu, Xuchen You, Soheil Feizi
With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influe…
Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks
Aya Abdelsalam Ismail, Mohamed Gunady, Luiz Pessoa +2
Recent efforts to improve the interpretability of deep neural networks use saliency to characterize the importance of input features to predictions made by models. Work on interpre…
Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks
Alexander Levine, Soheil Feizi
In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses con…
Deep k-NN Defense against Clean-label Data Poisoning Attacks
Neehar Peri, Neal Gupta, W. Ronny Huang +5
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples i…
Functional Adversarial Attacks
Cassidy Laidlaw, Soheil Feizi
We propose functional adversarial attacks, a novel class of threat models for crafting adversarial examples to fool machine learning models. Unlike a standard -ball threat…
Interpretable Adversarial Training for Text
Samuel Barham, Soheil Feizi
Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete na…
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…
Adversarially Robust Distillation
Micah Goldblum, Liam Fowl, Soheil Feizi +1
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This p…
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…
Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Yogesh Balaji, Rama Chellappa, Soheil Feizi
Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, w…
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…
Compressing GANs using Knowledge Distillation
Angeline Aguinaldo, Ping-Yeh Chiang, Alex Gain +3
Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art G…