research
∙
08/04/2023
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
Optical Character Recognition (OCR) enables automatic text extraction fr...
share
research
∙
03/21/2023
Effective Ambiguity Attack Against Passport-based DNN Intellectual Property Protection Schemes through Fully Connected Layer Substitution
Since training a deep neural network (DNN) is costly, the well-trained d...
research
∙
05/26/2021
Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services
Model protection is vital when deploying Convolutional Neural Networks (...
research
∙
05/08/2021
Self-Supervised Adversarial Example Detection by Disentangled Representation
Deep learning models are known to be vulnerable to adversarial examples ...
research
∙
03/07/2021