Search Results for author:
Found 2 papers, 0 papers with code
Practical and General Backdoor Attacks against Vertical Federated Learning
The main challenge of this attack is to allow an attacker without access to the data labels, to perform an effective attack.
DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints
Backdoor attack is a type of serious security threat to deep learning models. An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
