Differentially Private Continual Learning using Pre-Trained Models
- URL: http://arxiv.org/abs/2411.04680v2
- Date: Fri, 08 Nov 2024 06:47:39 GMT
- Title: Differentially Private Continual Learning using Pre-Trained Models
- Authors: Marlon Tobaben, Marcus Klasson, Rui Li, Arno Solin, Antti Honkela,
- Abstract summary: This work explores the intersection of continual learning (CL) and differential privacy (DP)
We propose using pre-trained models to address the trade-offs between privacy and performance in a continual learning setting.
- Score: 17.12787392937876
- License:
- Abstract: This work explores the intersection of continual learning (CL) and differential privacy (DP). Crucially, continual learning models must retain knowledge across tasks, but this conflicts with the differential privacy requirement of restricting individual samples to be memorised in the model. We propose using pre-trained models to address the trade-offs between privacy and performance in a continual learning setting. More specifically, we present necessary assumptions to enable privacy-preservation and propose combining pre-trained models with parameter-free classifiers and parameter-efficient adapters that are learned under differential privacy. Our experiments demonstrate their effectiveness and provide insights into balancing the competing demands of continual learning and privacy.
Related papers
- Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation [33.795122935686706]
We propose ANADP, a novel algorithm that adaptively allocates additive noise based on the importance of model parameters.
We demonstrate that ANADP narrows the performance gap between regular fine-tuning and traditional DP fine-tuning on a series of datasets.
arXiv Detail & Related papers (2024-10-03T19:02:50Z) - Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information.
We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting.
Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
arXiv Detail & Related papers (2023-09-15T17:10:51Z) - Tight Auditing of Differentially Private Machine Learning [77.38590306275877]
For private machine learning, existing auditing mechanisms are tight.
They only give tight estimates under implausible worst-case assumptions.
We design an improved auditing scheme that yields tight privacy estimates for natural (not adversarially crafted) datasets.
arXiv Detail & Related papers (2023-02-15T21:40:33Z) - An Ensemble Teacher-Student Learning Approach with Poisson Sub-sampling
to Differential Privacy Preserving Speech Recognition [51.20130423303659]
We propose an ensemble learning framework with Poisson sub-sampling to train a collection of teacher models to issue some differential privacy (DP) guarantee for training data.
Through boosting under DP, a student model derived from the training data suffers little model degradation from the models trained with no privacy protection.
Our proposed solution leverages upon two mechanisms, namely: (i) a privacy budget amplification via Poisson sub-sampling to train a target prediction model that requires less noise to achieve a same level of privacy budget, and (ii) a combination of the sub-sampling technique and an ensemble teacher-student learning framework.
arXiv Detail & Related papers (2022-10-12T16:34:08Z) - On the utility and protection of optimization with differential privacy
and classic regularization techniques [9.413131350284083]
We study the effectiveness of the differentially-private descent (DP-SGD) algorithm against standard optimization practices with regularization techniques.
We discuss differential privacy's flaws and limits and empirically demonstrate the often superior privacy-preserving properties of dropout and l2-regularization.
arXiv Detail & Related papers (2022-09-07T14:10:21Z) - SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles [50.90773979394264]
This paper studies a model that protects the privacy of individuals' sensitive information while also allowing it to learn non-discriminatory predictors.
A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
arXiv Detail & Related papers (2022-04-11T14:42:54Z) - Towards Differential Relational Privacy and its use in Question
Answering [109.4452196071872]
Memorization of relation between entities in a dataset can lead to privacy issues when using a trained question answering model.
We quantify this phenomenon and provide a possible definition of Differential Privacy (DPRP)
We illustrate concepts in experiments with largescale models for Question Answering.
arXiv Detail & Related papers (2022-03-30T22:59:24Z) - Statistical Privacy Guarantees of Machine Learning Preprocessing
Techniques [1.198727138090351]
We adapt a privacy violation detection framework based on statistical methods to measure privacy levels of machine learning pipelines.
We apply the newly created framework to show that resampling techniques used when dealing with imbalanced datasets cause the resultant model to leak more privacy.
arXiv Detail & Related papers (2021-09-06T14:08:47Z) - The Influence of Dropout on Membership Inference in Differentially
Private Models [0.0]
Differentially private models seek to protect the privacy of data the model is trained on.
We conduct membership inference attacks against models with and without differential privacy.
arXiv Detail & Related papers (2021-03-16T12:09:51Z) - Differentially Private and Fair Deep Learning: A Lagrangian Dual
Approach [54.32266555843765]
This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors.
The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
arXiv Detail & Related papers (2020-09-26T10:50:33Z) - Tempered Sigmoid Activations for Deep Learning with Differential Privacy [33.574715000662316]
We show that the choice of activation function is central to bounding the sensitivity of privacy-preserving deep learning.
We achieve new state-of-the-art accuracy on MNIST, FashionMNIST, and CIFAR10 without any modification of the learning procedure fundamentals.
arXiv Detail & Related papers (2020-07-28T13:19:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.