Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models

• URL: http://arxiv.org/abs/2411.15831v1
• Date: Sun, 24 Nov 2024 13:17:36 GMT
• Title: Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
• Authors: Olivia Ma, Jonathan Passerat-Palmbach, Dmitrii Usynin,
• Abstract summary: Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. Differential Privacy (DP) offers a solution to mitigate these risks, but introduces significant computational and performance trade-offs. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage.
• Score: 2.3281513013731145
• License:
• Abstract: Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it introduces significant computational and performance trade-offs, particularly with standard fine-tuning approaches. Previous work has primarily focused on full-parameter updates, which are computationally intensive and may not fully leverage DPs potential in large models. In this work, we address these shortcomings by investigating Parameter-Efficient Fine-Tuning (PEFT) methods under DP constraints. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage. Furthermore, we incorporate a data poisoning experiment involving intentional mislabelling to assess model memorisation and directly measure privacy risks. Our findings indicate that PEFT methods not only provide a promising alternative but also serve as a complementary approach for privacy-preserving, resource-efficient fine-tuning of LLMs.

Related papers

• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• 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)
• Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models [21.1164927055712]
  Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP) Our study explores DP parameter-efficient fine-tuning as a way to mitigate privacy risks with smaller computation and performance costs for ASR models.
  arXiv  Detail & Related papers  (2024-10-02T18:49:15Z)
• Differentially Private Fine-Tuning of Diffusion Models [22.454127503937883]
  The integration of Differential Privacy with diffusion models (DMs) presents a promising yet challenging frontier. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data. We propose a strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off.
  arXiv  Detail & Related papers  (2024-06-03T14:18:04Z)
• Automated discovery of trade-off between utility, privacy and fairness in machine learning models [8.328861861105889]
  We show how PFairDP can be used to replicate known results that were achieved through manual constraint setting process. We further demonstrate effectiveness of PFairDP with experiments on multiple models and datasets.
  arXiv  Detail & Related papers  (2023-11-27T10:28:44Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens [10.727571921061024]
  Differentially Private Descent Gradient (DPSGD) is the state-of-the-art method to train privacy-preserving models. With a drop-in replacement of the activation function, we achieve new state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2023-03-03T09:59:42Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• Large Language Models Can Be Strong Differentially Private Learners [70.0317718115406]
  Differentially Private (DP) learning has seen limited success for building large deep learning models of text. We show that this performance drop can be mitigated with the use of large pretrained models. We propose a memory saving technique that allows clipping in DP-SGD to run without instantiating per-example gradients.
  arXiv  Detail & Related papers  (2021-10-12T01:45:27Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

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.