# Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

arXiv: https://arxiv.org/abs/1709.05750 · HTML: https://mlsanity.com/paper/1709.05750/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2017.

## Built on by (most cited first, 30 of 34)

- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [FederatedScope: A Flexible Federated Learning Platform for Heterogeneity](https://mlsanity.com/paper/2204.05011/) (2022)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [LLM-PBE: Assessing Data Privacy in Large Language Models](https://mlsanity.com/paper/2408.12787/) (2024)
- [GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning](https://mlsanity.com/paper/2105.00529/) (2021)
- [On the Convergence and Calibration of Deep Learning with Differential Privacy](https://mlsanity.com/paper/2106.07830/) (2021)
- [Gradient Leakage Attack Resilient Deep Learning](https://mlsanity.com/paper/2112.13178/) (2021)
- [Differentially Private Counterfactuals via Functional Mechanism](https://mlsanity.com/paper/2208.02878/) (2022)
- [Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey](https://mlsanity.com/paper/2309.16398/) (2023)
- [DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release](https://mlsanity.com/paper/2311.14056/) (2023)
- [Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability](https://mlsanity.com/paper/2107.08461/) (2021)
- [Continual Learning with Differential Privacy](https://mlsanity.com/paper/2110.05223/) (2021)
- [Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design](https://mlsanity.com/paper/2111.14924/) (2021)
- [Task-aware Privacy Preservation for Multi-dimensional Data](https://mlsanity.com/paper/2110.02329/) (2021)
- [Unlearnable Examples For Time Series](https://mlsanity.com/paper/2402.02028/) (2024)
- [ConfounderGAN: Protecting Image Data Privacy with Causal Confounder](https://mlsanity.com/paper/2212.01767/) (2022)
- [FairDP: Certified Fairness with Differential Privacy](https://mlsanity.com/paper/2305.16474/) (2023)
- [Multi-Party Dual Learning](https://mlsanity.com/paper/2104.06677/) (2021)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning](https://mlsanity.com/paper/2207.12831/) (2022)
- [DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling](https://mlsanity.com/paper/2205.12718/) (2022)
- [Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systems](https://mlsanity.com/paper/2401.02450/) (2024)
- [Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defenses](https://mlsanity.com/paper/2502.04201/) (2025)
- [Partial sensitivity analysis in differential privacy](https://mlsanity.com/paper/2109.10582/) (2021)
- [Differential Privacy May Have a Potential Optimization Effect on Some Swarm Intelligence Algorithms besides Privacy-preserving](https://mlsanity.com/paper/2306.17370/) (2023)
- [Effectiveness of L2 Regularization in Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2412.01541/) (2024)
- [PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction](https://mlsanity.com/paper/2507.00230/) (2025)
- [Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response](https://mlsanity.com/paper/2509.13987/) (2025)
- [Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy](https://mlsanity.com/paper/2605.16812/) (2026)

## Abstract (arXiv)

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.