83 citations · 226 across the 17 of their papers we have counts for
20 papers
Locally optimal detection of stochastic targeted universal adversarial perturbations
Amish Goel, Pierre Moulin
Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood r…
Robust Machine Learning via Privacy/Rate-Distortion Theory
Ye Wang, Shuchin Aeron, Adnan Siraj Rakin +2
Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between opti…
Detecting Audio Attacks on ASR Systems with Dropout Uncertainty
Tejas Jayashankar, Jonathan Le Roux, Pierre Moulin
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncer…
Faster Subgradient Methods for Functions with Hölderian Growth
Patrick R. Johnstone, Pierre Moulin
The purpose of this manuscript is to derive new convergence results for several subgradient methods applied to minimizing nonsmooth convex functions with Hölderian growth. The grow…
Convergence Rates of Inertial Splitting Schemes for Nonconvex Composite Optimization
Patrick R. Johnstone, Pierre Moulin
We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka--Łojazie…
On Information-Theoretic Characterizations of Markov Random Fields and Subfields
Raymond W. Yeung, Ali Al-Bashabsheh, Chao Chen +2
Let form a Markov random field (MRF) represented by an undirected graph , and be a subset of . We determine the smallest graph that can always rep…