Robustness Certification of Generative Models

04/30/2020
by   Matthew Mirman, et al.
0

Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resulting path in the image manifold satisfy a given property can be very challenging. This is because this set is highly non-convex, thwarting existing scalable robustness analysis methods, which are often based on convex relaxations. We present ApproxLine, a scalable certification method that successfully verifies non-trivial specifications involving generative models and classifiers. ApproxLine can provide both sound deterministic and probabilistic guarantees, by capturing either infinite non-convex sets of neural network activation vectors or distributions over such sets. We show that ApproxLine is practically useful and can verify interesting interpolations in the networks latent space.

READ FULL TEXT

Authors

page 8

page 14

01/30/2021

Atlas Generative Models and Geodesic Interpolation

Generative neural networks have a well recognized ability to estimate un...
05/27/2019

Universality Theorems for Generative Models

Despite the fact that generative models are extremely successful in prac...
02/09/2021

Using Deep LSD to build operators in GANs latent space with meaning in real space

Generative models rely on the key idea that data can be represented in t...
12/03/2018

Exploring galaxy evolution with generative models

Context. Generative models open up the possibility to interrogate scient...
05/31/2022

Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry

Deep generative models can automatically create content of diverse types...
06/05/2018

On Latent Distributions Without Finite Mean in Generative Models

We investigate the properties of multidimensional probability distributi...
12/16/2020

Generate and Verify: Semantically Meaningful Formal Analysis of Neural Network Perception Systems

Testing remains the primary method to evaluate the accuracy of neural ne...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.