Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning.

Arezoo Rajabi Bhaskar Ramasubramanian Radha Poovendran

Published in: CoRR (2022)

Keyphrases

deep learning
deep architectures
restricted boltzmann machine
unsupervised learning
deep belief networks
denial of service attacks
unsupervised feature learning
data sets
machine learning
weakly supervised
network security
mental models
information retrieval