activity
20192022
most citedQuantifying Perceptual Distortion of Adversarial Examples

31 citations · 51 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2022

Zonotope Domains for Lagrangian Neural Network Verification

Matt Jordan, Jonathan Hayase, Alexandros G. Dimakis +1

Neural network verification aims to provide provable bounds for the output of a neural network for a given input range. Notable prior works in this domain have either generated bou…

cs.LG2021

Inverse Problems Leveraging Pre-trained Contrastive Representations

Sriram Ravula, Georgios Smyrnis, Matt Jordan +1

We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on…

cs.LG20211 cited

Provable Lipschitz Certification for Generative Models

Matt Jordan, Alexandros G. Dimakis

We present a scalable technique for upper bounding the Lipschitz constant of generative models. We relate this quantity to the maximal norm over the set of attainable vector-Jacobi…

cs.SI2020

Quarantines as a Targeted Immunization Strategy

Jessica Hoffmann, Matt Jordan, Constantine Caramanis

In the context of the recent COVID-19 outbreak, quarantine has been used to "flatten the curve" and slow the spread of the disease. In this paper, we show that this is not the only…

stat.ML2020

Exactly Computing the Local Lipschitz Constant of ReLU Networks

Matt Jordan, Alexandros G. Dimakis

The local Lipschitz constant of a neural network is a useful metric with applications in robustness, generalization, and fairness evaluation. We provide novel analytic results rela…

cs.LG201919 cited

Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes

Matt Jordan, Justin Lewis, Alexandros G. Dimakis

We propose a novel method for computing exact pointwise robustness of deep neural networks for all convex norms. Our algorithm, GeoCert, finds the largest ball ce…