Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons.

Chandresh Pravin Ivan Martino Giuseppe Nicosia Varun Ojha

Published in: CoRR (2022)

Keyphrases

deep learning
semi fragile watermarking
unsupervised feature learning
unsupervised learning
machine learning
neural network
weakly supervised
restricted boltzmann machine
mental models
data sets
training data
watermarking scheme
deep architectures