Towards Differentially Private Text Representations

• URL: http://arxiv.org/abs/2006.14170v1
• Date: Thu, 25 Jun 2020 04:42:18 GMT
• Title: Towards Differentially Private Text Representations
• Authors: Lingjuan Lyu, Yitong Li, Xuanli He, Tong Xiao
• Abstract summary: We develop a new deep learning framework under an untrusted server setting. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $epsilon$ on accuracy. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols.
• Score: 52.64048365919954
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $\epsilon$ on accuracy, and provide enhanced flexibility in choosing randomization probabilities for LDP. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols, demonstrating the advantages of our LDP protocol.

Related papers

• CURE: Privacy-Preserving Split Learning Done Right [1.388112207221632]
  Homomorphic encryption (HE)-based solutions exist for this scenario but often impose prohibitive computational burdens. CURE is a novel system that encrypts only the server side of the model and the data. We demonstrate CURE can achieve similar accuracy to plaintext SL while being 16x more efficient in terms of the runtime.
  arXiv  Detail & Related papers  (2024-07-12T04:10:19Z)
• PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning [49.916365792036636]
  Federated learning (FL) has recently gained significant momentum due to its potential to leverage large-scale distributed user data. The transmitted model updates can potentially leak sensitive user information, and the lack of central control of the local training process leaves the global model susceptible to malicious manipulations on model updates. We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy.
  arXiv  Detail & Related papers  (2024-07-12T03:18:08Z)
• DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation [15.023077875990614]
  Federated learning (FL) allows clients to collaboratively train a global model without sharing their local data with a server. Differential privacy (DP) addresses such leakage by providing formal privacy guarantees, with mechanisms that add randomness to the clients' contributions. We propose an adaptation method that can be combined with differential privacy and call it DP-DyLoRA.
  arXiv  Detail & Related papers  (2024-05-10T10:10:37Z)
• FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity [82.5448598805968]
  We present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies.
  arXiv  Detail & Related papers  (2024-04-15T14:14:05Z)
• Tunable Soft Prompts are Messengers in Federated Learning [55.924749085481544]
  Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources. The lack of model privacy protection in FL becomes an unneglectable challenge. We propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts.
  arXiv  Detail & Related papers  (2023-11-12T11:01:10Z)
• Blockchain-based Optimized Client Selection and Privacy Preserved Framework for Federated Learning [2.4201849657206496]
  Federated learning is a distributed mechanism that trained large-scale neural network models with the participation of multiple clients. With this feature, federated learning is considered a secure solution for data privacy issues. We proposed the blockchain-based optimized client selection and privacy-preserved framework.
  arXiv  Detail & Related papers  (2023-07-25T01:35:51Z)
• 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)
• EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party [7.873139977724476]
  Federated learning allows multiple participants to conduct joint modeling without disclosing their local data. We propose a novel VFL framework without a third party called EFMVFL. Our framework is secure, more efficient, and easy to be extended to multiple participants.
  arXiv  Detail & Related papers  (2022-01-17T07:06:21Z)
• A Bayesian Federated Learning Framework with Online Laplace Approximation [144.7345013348257]
  Federated learning allows multiple clients to collaboratively learn a globally shared model. We propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. We achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
  arXiv  Detail & Related papers  (2021-02-03T08:36:58Z)
• LDP-Fed: Federated Learning with Local Differential Privacy [14.723892247530234]
  We present LDP-Fed, a novel federated learning system with a formal privacy guarantee using local differential privacy (LDP) Existing LDP protocols are developed primarily to ensure data privacy in the collection of single numerical or categorical values. In federated learning model parameter updates are collected iteratively from each participant.
  arXiv  Detail & Related papers  (2020-06-05T19:15:13Z)

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.