69 citations · 222 across the 18 of their papers we have counts for
15 papers · 1 filter
Goal-Conditioned Q-Learning as Knowledge Distillation
Alexander Levine, Soheil Feizi
Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during t…
Lethal Dose Conjecture on Data Poisoning
Wenxiao Wang, Alexander Levine, Soheil Feizi
Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding…
Provable Adversarial Robustness for Fractional Lp Threat Models
Alexander Levine, Soheil Feizi
In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks…
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
Wenxiao Wang, Alexander Levine, Soheil Feizi
Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), w…
Certifying Model Accuracy under Distribution Shifts
Aounon Kumar, Alexander Levine, Tom Goldstein +1
Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this…
Policy Smoothing for Provably Robust Reinforcement Learning
Aounon Kumar, Alexander Levine, Soheil Feizi
The study of provable adversarial robustness for deep neural networks (DNNs) has mainly focused on static supervised learning tasks such as image classification. However, DNNs have…
Improved, Deterministic Smoothing for L_1 Certified Robustness
Alexander Levine, Soheil Feizi
Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothi…
Certifying Confidence via Randomized Smoothing
Aounon Kumar, Alexander Levine, Soheil Feizi +1
Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. It uses the probabilities of predicting the top tw…
Tight Second-Order Certificates for Randomized Smoothing
Alexander Levine, Aounon Kumar, Thomas Goldstein +1
Randomized smoothing is a popular way of providing robustness guarantees against adversarial attacks: randomly-smoothed functions have a universal Lipschitz-like bound, allowing fo…
Deep Partition Aggregation: Provable Defense against General Poisoning Attacks
Alexander Levine, Soheil Feizi
Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, whic…
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks
Alexander Levine, Soheil Feizi
Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model…
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
Aounon Kumar, Alexander Levine, Tom Goldstein +1
Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against -norm bounded adversaries. In this w…
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…
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…
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…