Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
Title | Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning |
Publication Type | Conference Paper |
Year of Publication | 2017 |
Authors | Phan, N., Wu, X., Hu, H., Dou, D. |
Conference Name | 2017 IEEE International Conference on Data Mining (ICDM) |
ISBN Number | 978-1-5386-3835-4 |
Keywords | adaptive Laplace mechanism, affine transformations, affine transforms, AI, artificial intelligence, Biological neural networks, Computational modeling, data privacy, Deep Learning, deep neural networks, Differential privacy, differential privacy preservation, Human Behavior, human factor, human factors, Laplace Mechanism, Laplace transforms, learning (artificial intelligence), loss functions, machine learning, neural nets, Neurons, privacy, privacy budget consumption, pubcrawl, resilience, Resiliency, Scalability, Training, training steps |
Abstract | In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions. |
URL | https://ieeexplore.ieee.org/document/8215511 |
DOI | 10.1109/ICDM.2017.48 |
Citation Key | phan_adaptive_2017 |
- Laplace Mechanism
- training steps
- Training
- Scalability
- Resiliency
- resilience
- pubcrawl
- privacy budget consumption
- privacy
- Neurons
- neural nets
- machine learning
- loss functions
- learning (artificial intelligence)
- Laplace transforms
- adaptive Laplace mechanism
- Human Factors
- human factor
- Human behavior
- differential privacy preservation
- differential privacy
- deep neural networks
- deep learning
- data privacy
- Computational modeling
- Biological neural networks
- Artificial Intelligence
- AI
- affine transforms
- affine transformations