Defending against neural network model stealing attacks using deceptive perturbations

T Lee, B Edwards, I Molloy, D Su - 2019 IEEE Security and …, 2019 - ieeexplore.ieee.org
Machine learning architectures are readily available, but obtaining the high quality labeled
data for training is costly. Pre-trained models available as cloud services can be used to …
被引用次数：99 相关文章

Defending against neural network model stealing attacks using deceptive perturbations

T Lee, B Edwards, I Molloy, D Su - IEEE Symposium on Security …, 2019 - research.ibm.com
Abstract Machine learning architectures are readily available, but obtaining the high quality
labeled data for training is costly. Pre-trained models available as cloud services can be …

Defending Against Neural Network Model Stealing Attacks Using Deceptive Perturbations

T Lee, B Edwards, I Molloy, D Su - 2019 IEEE Security and Privacy …, 2019 - computer.org
Abstract Machine learning architectures are readily available, but obtaining the high quality
labeled data for training is costly. Pre-trained models available as cloud services can be …
[PDF] researchgate.net

[PDF][PDF] Defending Against Neural Network Model Stealing Attacks Using Deceptive Perturbations

T Lee, B Edwards, I Molloy, D Su - 2019 - researchgate.net
Machine learning architectures are readily available, but obtaining the high quality labeled
data for training is costly. Pre-trained models available as cloud services can be used to …