
SecondOrder Group Influence Functions for BlackBox Predictions
With the rapid adoption of machine learning systems in sensitive applica...
read it

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation
Recently, techniques have been developed to provably guarantee the robus...
read it

InputCell Attention Reduces Vanishing Saliency of Recurrent Neural Networks
Recent efforts to improve the interpretability of deep neural networks u...
read it

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Building on the success of deep learning, two modern approaches to learn...
read it

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks
Patch adversarial attacks on images, in which the attacker can distort p...
read it

Understanding Impacts of HighOrder Loss Approximations and Features in Deep Learning Interpretation
Current methods to interpret deep learning models by generating saliency...
read it

Understanding GANs: the LQG Setting
Generative Adversarial Networks (GANs) have become a popular method to l...
read it

Porcupine Neural Networks: (Almost) All Local Optima are Global
Neural networks have been used prominently in several machine learning a...
read it

Maximally Correlated Principal Component Analysis
In the era of big data, reducing data dimensionality is critical in many...
read it

Network Maximal Correlation
We introduce Network Maximal Correlation (NMC) as a multivariate measure...
read it

Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs
A latent space model for a family of random graphs assigns realvalued v...
read it

Are adversarial examples inevitable?
A wide range of defenses have been proposed to harden neural networks ag...
read it

Robustness Certificates Against Adversarial Examples for ReLU Networks
While neural networks have achieved high performance in different learni...
read it

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Understanding proper distance measures between distributions is at the c...
read it

Compressing GANs using Knowledge Distillation
Generative Adversarial Networks (GANs) have been used in several machine...
read it

Adversarially Robust Distillation
Knowledge distillation is effective for producing small highperformance...
read it

Certifiably Robust Interpretation in Deep Learning
Although gradientbased saliency maps are popular methods for deep learn...
read it

Functional Adversarial Attacks
We propose functional adversarial attacks, a novel class of threat model...
read it

Interpretable Adversarial Training for Text
Generating highquality and interpretable adversarial examples in the te...
read it

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks
In the last couple of years, several adversarial attack methods based on...
read it

Quantum Wasserstein Generative Adversarial Networks
The study of quantum generative models is wellmotivated, not only becau...
read it

Adversarial Robustness of FlowBased Generative Models
Flowbased generative models leverage invertible generator functions to ...
read it

Bounding Singular Values of Convolution Layers
In deep neural networks, the spectral norm of the Jacobian of a layer bo...
read it

Strong Baseline Defenses Against CleanLabel Poisoning Attacks
Targeted cleanlabel poisoning is a type of adversarial attack on machin...
read it

Playing it Safe: Adversarial Robustness with an Abstain Option
We explore adversarial robustness in the setting in which it is acceptab...
read it

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
Randomized smoothing, using just a simple isotropic Gaussian distributio...
read it

Subadditivity of Probability Divergences on BayesNets with Applications to Time Series GANs
GANs for time series data often use sliding windows or selfattention to...
read it
Soheil Feizi
is this you? claim profile