No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learning

• URL: http://arxiv.org/abs/2406.01080v1
• Date: Mon, 3 Jun 2024 07:59:10 GMT
• Title: No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learning
• Authors: Zhibo Xing, Zijian Zhang, Zi'ang Zhang, Jiamou Liu, Liehuang Zhu, Giovanni Russello,
• Abstract summary: Federated learning allows several clients to train one machine learning model jointly without sharing private data, providing privacy protection. Traditional federated learning is vulnerable to poisoning attacks, which can not only decrease the model performance, but also implant malicious backdoors. In this paper, we aim to build a privacy-preserving and Byzantine-robust federated learning scheme to provide an environment with no vandalism (NoV) against attacks from malicious participants.
• Score: 18.1129191782913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning allows several clients to train one machine learning model jointly without sharing private data, providing privacy protection. However, traditional federated learning is vulnerable to poisoning attacks, which can not only decrease the model performance, but also implant malicious backdoors. In addition, direct submission of local model parameters can also lead to the privacy leakage of the training dataset. In this paper, we aim to build a privacy-preserving and Byzantine-robust federated learning scheme to provide an environment with no vandalism (NoV) against attacks from malicious participants. Specifically, we construct a model filter for poisoned local models, protecting the global model from data and model poisoning attacks. This model filter combines zero-knowledge proofs to provide further privacy protection. Then, we adopt secret sharing to provide verifiable secure aggregation, removing malicious clients that disrupting the aggregation process. Our formal analysis proves that NoV can protect data privacy and weed out Byzantine attackers. Our experiments illustrate that NoV can effectively address data and model poisoning attacks, including PGD, and outperforms other related schemes.

Related papers

• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Privacy Backdoors: Stealing Data with Corrupted Pretrained Models [23.54726973460633]
  Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. We show how to build privacy backdoors for a variety of models, including transformers.
  arXiv  Detail & Related papers  (2024-03-30T20:43:53Z)
• FedDefender: Client-Side Attack-Tolerant Federated Learning [60.576073964874]
  Federated learning enables learning from decentralized data sources without compromising privacy. It is vulnerable to model poisoning attacks, where malicious clients interfere with the training process. We propose a new defense mechanism that focuses on the client-side, called FedDefender, to help benign clients train robust local models.
  arXiv  Detail & Related papers  (2023-07-18T08:00:41Z)
• RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense [9.806681555309519]
  Federated learning (FL) allows clients to collaboratively train a model without sharing their private data. Recent studies have shown that private information can still be leaked through shared gradients. We propose a user-configurable privacy defense, RecUP-FL, that can better focus on the user-specified sensitive attributes.
  arXiv  Detail & Related papers  (2023-04-11T10:59:45Z)
• Students Parrot Their Teachers: Membership Inference on Model Distillation [54.392069096234074]
  We study the privacy provided by knowledge distillation to both the teacher and student training sets. Our attacks are strongest when student and teacher sets are similar, or when the attacker can poison the teacher set.
  arXiv  Detail & Related papers  (2023-03-06T19:16:23Z)
• CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning [77.27443885999404]
  Federated Learning (FL) is a setting for training machine learning models in distributed environments. We propose a novel method, CANIFE, that uses carefully crafted samples by a strong adversary to evaluate the empirical privacy of a training round.
  arXiv  Detail & Related papers  (2022-10-06T13:30:16Z)
• A New Implementation of Federated Learning for Privacy and Security Enhancement [27.612480082254486]
  Federated learning (FL) has emerged as a new machine learning setting. No local data needs to be shared, and privacy can be well protected. We propose a model update based federated averaging algorithm to defend against Byzantine attacks.
  arXiv  Detail & Related papers  (2022-08-03T03:13:19Z)
• Defense Against Gradient Leakage Attacks via Learning to Obscure Data [48.67836599050032]
  Federated learning is considered as an effective privacy-preserving learning mechanism. In this paper, we propose a new defense method to protect the privacy of clients' data by learning to obscure data.
  arXiv  Detail & Related papers  (2022-06-01T21:03:28Z)
• Defending against Reconstruction Attacks with R\'enyi Differential Privacy [72.1188520352079]
  Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. Differential privacy is a known solution to such attacks, but is often used with a relatively large privacy budget. We show that, for a same mechanism, we can derive privacy guarantees for reconstruction attacks that are better than the traditional ones from the literature.
  arXiv  Detail & Related papers  (2022-02-15T18:09:30Z)
• Secure and Privacy-Preserving Federated Learning via Co-Utility [7.428782604099875]
  We build a federated learning framework that offers privacy to the participating peers and security against Byzantine and poisoning attacks. Unlike privacy protection via update aggregation, our approach preserves the values of model updates and hence the accuracy of plain federated learning.
  arXiv  Detail & Related papers  (2021-08-04T08:58:24Z)
• Federated Learning in Adversarial Settings [0.8701566919381224]
  Federated learning scheme provides different trade-offs between robustness, privacy, bandwidth efficiency, and model accuracy. We show that this extension performs as efficiently as the non-private but robust scheme, even with stringent privacy requirements. This suggests a possible fundamental trade-off between Differential Privacy and robustness.
  arXiv  Detail & Related papers  (2020-10-15T14:57:02Z)

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.