-
On Need for Topology-Aware Generative Models for Manifold-Based Defenses
ML algorithms or models, especially deep neural networks (DNNs), have sh...
read it
-
Universality Theorems for Generative Models
Despite the fact that generative models are extremely successful in prac...
read it
-
Flow-based Generative Models for Learning Manifold to Manifold Mappings
Many measurements or observations in computer vision and machine learnin...
read it
-
Learning Generative Models across Incomparable Spaces
Generative Adversarial Networks have shown remarkable success in learnin...
read it
-
Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
Simulators that generate observations based on theoretical models can be...
read it
-
Intrinsic Multi-scale Evaluation of Generative Models
Generative models are often used to sample high-dimensional data points ...
read it
-
Anomaly scores for generative models
Reconstruction error is a prevalent score used to identify anomalous sam...
read it
On Need for Topology Awareness of Generative Models
Manifold assumption in learning states that: the data lie approximately on a manifold of much lower dimension than the input space. Generative models learn to generate data according to the underlying data distribution. Generative models are used in various tasks, such as data augmentation and generating variation of images. This paper addresses the following question: do generative models need to be aware of the topology of the underlying data manifold in which the data lie? This paper suggests that the answer is yes and demonstrates that these can have ramifications on security-critical applications, such as generative-model based defenses for adversarial examples. We provide theoretical and experimental results to support our claims.
READ FULL TEXT
Comments
There are no comments yet.