research
∙
05/26/2021
Pattern Detection in the Activation Space for Identifying Synthesized Content
Generative Adversarial Networks (GANs) have recently achieved unpreceden...
share
research
∙
04/01/2021
Towards creativity characterization of generative models via group-based subset scanning
Deep generative models, such as Variational Autoencoders (VAEs), have be...
research
∙
02/13/2020
Identifying Audio Adversarial Examples via Anomalous Pattern Detection
Audio processing models based on deep neural networks are susceptible to...
research
∙
12/08/2017