Backdoor smoothing: Demystifying backdoor attacks on deep neural networks

Backdoor smoothing: Demystifying backdoor attacks on deep neural networks

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by injecting poisoning samples containing the trigger into the training...

Full description

Bibliographic Details
Main Authors: Backes, M. (Author), Biggio, B. (Author), Grosse, K. (Author), Lee, T. (Author), Molloy, I. (Author), Park, Y. (Author)
Format: Article
Language:English
Published: Elsevier Ltd 2022
Subjects:
Backdoors
Deep learning backdoor
Deep learning backdoors
Deep neural networks
Input sample
Learning algorithms
Machine learning models
ML poisoning
ML security
Training time
Training time attack
Training time attacks
Training time defense
Training time defenses
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items