Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

September 18, 2017 Β· Declared Dead Β· πŸ› Industrial Conference on Data Mining

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors NhatHai Phan, Xintao Wu, Han Hu, Dejing Dou arXiv ID 1709.05750 Category cs.CR: Cryptography & Security Cross-listed cs.LG, stat.ML Citations 208 Venue Industrial Conference on Data Mining Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted