# Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning

arXiv: https://arxiv.org/abs/2207.12831 · HTML: https://mlsanity.com/paper/2207.12831/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 26 Jul 2022.

## Builds on (most cited first, 30 of 30)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [Conditional Channel Gated Networks for Task-Aware Continual Learning](https://mlsanity.com/paper/2004.00070/) (2020)
- [iTAML: An Incremental Task-Agnostic Meta-learning Approach](https://mlsanity.com/paper/2003.11652/) (2020)
- [Towards the Science of Security and Privacy in Machine Learning](https://mlsanity.com/paper/1611.03814/) (2016)
- [Learning latent representations across multiple data domains using Lifelong VAEGAN](https://mlsanity.com/paper/2007.10221/) (2020)
- [Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning](https://mlsanity.com/paper/1709.05750/) (2017)
- [XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning](https://mlsanity.com/paper/2003.08561/) (2020)
- [Deep learning for neuroimaging: a validation study](https://mlsanity.com/paper/1312.5847/) (2013)
- [Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing](https://mlsanity.com/paper/2101.00509/) (2021)
- [Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness](https://mlsanity.com/paper/1906.01444/) (2019)
- [Online Continual Learning Via Candidates Voting](https://mlsanity.com/paper/2110.08855/) (2021)
- [Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform](https://mlsanity.com/paper/1909.01502/) (2019)
- [Preserving Differential Privacy in Convolutional Deep Belief Networks](https://mlsanity.com/paper/1706.08839/) (2017)
- [Convolutional Neural Networks on Randomized Data](https://mlsanity.com/paper/1907.10935/) (2019)
- [Continual Learning with Differential Privacy](https://mlsanity.com/paper/2110.05223/) (2021)
- [On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches](https://mlsanity.com/paper/1708.08022/) (2017)
- [Differentially Private Continual Learning](https://mlsanity.com/paper/1902.06497/) (2019)

## Built on by (most cited first, 2 of 2)

- [Privacy-Aware Lifelong Learning](https://mlsanity.com/paper/2505.10941/) (2025)
- [Data Security in Large Language Models: Risks, Defense, and Directions](https://mlsanity.com/paper/2508.02312/) (2025)

## Abstract (arXiv)

In this paper, we show that the process of continually learning new tasks and memorizing previous tasks introduces unknown privacy risks and challenges to bound the privacy loss. Based upon this, we introduce a formal definition of Lifelong DP, in which the participation of any data tuples in the training set of any tasks is protected, under a consistently bounded DP protection, given a growing stream of tasks. A consistently bounded DP means having only one fixed value of the DP privacy budget, regardless of the number of tasks. To preserve Lifelong DP, we propose a scalable and heterogeneous algorithm, called L2DP-ML with a streaming batch training, to efficiently train and continue releasing new versions of an L2M model, given the heterogeneity in terms of data sizes and the training order of tasks, without affecting DP protection of the private training set. An end-to-end theoretical analysis and thorough evaluations show that our mechanism is significantly better than baseline approaches in preserving Lifelong DP. The implementation of L2DP-ML is available at: https://github.com/haiphanNJIT/PrivateDeepLearning.