Title | ||
---|---|---|
Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks |
Abstract | ||
---|---|---|
This paper proposes an ensemble learning model that is resistant to adversarial attacks. To build resilience, we introduced a training process where each member learns a radically distinct latent space. Member models are added one at a time to the ensemble. Simultaneously, the loss function is regulated by a reverse knowledge distillation, forcing the new member to learn different features and map... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ISQED51717.2021.9424353 | 2021 22nd International Symposium on Quality Electronic Design (ISQED) |
Keywords | DocType | ISSN |
Resistance,Training,Resists,Feature extraction,Extraterrestrial measurements,Robustness,Security | Conference | 1948-3287 |
ISBN | Citations | PageRank |
978-1-7281-7641-3 | 1 | 0.38 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ali Mirzaeian | 1 | 2 | 1.07 |
Jana Kosecká | 2 | 1523 | 129.85 |
Houman Homayoun | 3 | 579 | 69.64 |
Tinoosh Mohsenin | 4 | 1 | 0.38 |
Avesta Sasan | 5 | 228 | 28.57 |