mlsanityData to 14 Oct 2026

Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

arXiv 1709.05750 ↗First posted 18 Sep 2017cs.CR cs.LG stat.MLcited by 34

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 6; 2024: 4; 2025: 3; 2026: 5.

34 papers.

Sort:

By area:

  1. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  3. 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
  4. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 51
  5. 2024LLM-PBE: Assessing Data Privacy in Large Language Modelscited by 41
  6. 2021GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learningcited by 36
  7. 2021On the Convergence and Calibration of Deep Learning with Differential Privacycited by 36
  8. 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
  9. 2022Differentially Private Counterfactuals via Functional Mechanismcited by 13
  10. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  11. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 10
  12. 2021Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliabilitycited by 6
22 more
  1. 2021Continual Learning with Differential Privacycited by 6
  2. 2021Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Designcited by 6
  3. 2021Task-aware Privacy Preservation for Multi-dimensional Datacited by 5
  4. 2024Unlearnable Examples For Time Seriescited by 5
  5. 2022ConfounderGAN: Protecting Image Data Privacy with Causal Confoundercited by 4
  6. 2023FairDP: Certified Fairness with Differential Privacycited by 4
  7. 2021Multi-Party Dual Learningcited by 3
  8. 2023Adversarial Robustness in Unsupervised Machine Learning: A Systematic Reviewcited by 3
  9. 2022Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learningcited by 2
  10. 2022DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Poolingcited by 1
  11. 2024Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systemscited by 1
  12. 2025Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defensescited by 1
  13. 2021Partial sensitivity analysis in differential privacycited by 0
  14. 2023Differential Privacy May Have a Potential Optimization Effect on Some Swarm Intelligence Algorithms besides Privacy-preservingcited by 0
  15. 2024Effectiveness of L2 Regularization in Privacy-Preserving Machine Learningcited by 0
  16. 2025PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstructioncited by 0
  17. 2025Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Responsecited by 0
  18. 2026Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacycited by 0
  19. 2026An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guaranteescited by 0
  20. 2026Revisiting Privacy Amplification by Subsampling in Selective Release DPSGDcited by 0
  21. 2026Auditing Privacy Risks in LLM-Enhanced Graph Neural Networkscited by 0
  22. 2026Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocolscited by 0