Do We Really Need to Design New Byzantine-robust Aggregation Rules?

• URL: http://arxiv.org/abs/2501.17381v1
• Date: Wed, 29 Jan 2025 02:28:03 GMT
• Title: Do We Really Need to Design New Byzantine-robust Aggregation Rules?
• Authors: Minghong Fang, Seyedsina Nabavirazavi, Zhuqing Liu, Wei Sun, Sundararaja Sitharama Iyengar, Haibo Yang,
• Abstract summary: Federated learning (FL) allows multiple clients to collaboratively train a global machine learning model through a server. The decentralized aspect of FL makes it susceptible to poisoning attacks, where malicious clients can manipulate the global model. We present FoundationFL, a novel defense mechanism against poisoning attacks.
• Score: 9.709243052112921
• License:
• Abstract: Federated learning (FL) allows multiple clients to collaboratively train a global machine learning model through a server, without exchanging their private training data. However, the decentralized aspect of FL makes it susceptible to poisoning attacks, where malicious clients can manipulate the global model by sending altered local model updates. To counter these attacks, a variety of aggregation rules designed to be resilient to Byzantine failures have been introduced. Nonetheless, these methods can still be vulnerable to sophisticated attacks or depend on unrealistic assumptions about the server. In this paper, we demonstrate that there is no need to design new Byzantine-robust aggregation rules; instead, FL can be secured by enhancing the robustness of well-established aggregation rules. To this end, we present FoundationFL, a novel defense mechanism against poisoning attacks. FoundationFL involves the server generating synthetic updates after receiving local model updates from clients. It then applies existing Byzantine-robust foundational aggregation rules, such as Trimmed-mean or Median, to combine clients' model updates with the synthetic ones. We theoretically establish the convergence performance of FoundationFL under Byzantine settings. Comprehensive experiments across several real-world datasets validate the efficiency of our FoundationFL method.

Related papers

• BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption [0.0]
  Federated learning (FL) is a privacy-preserving edge-to-cloud technique used for training and deploying AI models on edge devices. BlindFL is a framework for global model aggregation in which clients encrypt and send a subset of their local model update. BlindFL significantly impedes client-side model poisoning attacks, a first for single-key, FHE-based FL schemes.
  arXiv  Detail & Related papers  (2025-01-20T18:42:21Z)
• Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective [65.65471972217814]
  federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively. FR has a unique sparse aggregation mechanism, where the embedding of each item is updated by only partial clients, instead of full clients in a dense aggregation of general FL. In this paper, we reformulate the Byzantine robustness under sparse aggregation by defining the aggregation for a single item as the smallest execution unit. We propose a family of effective attack strategies, named Spattack, which exploit the vulnerability in sparse aggregation and are categorized along the adversary's knowledge and capability.
  arXiv  Detail & Related papers  (2025-01-06T15:19:26Z)
• Byzantine-Robust Decentralized Federated Learning [30.33876141358171]
  Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private data. Decentralized learning (DFL) architecture has been proposed to allow clients to train models collaboratively in a serverless and peer-to-peer manner. DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients. We propose a new algorithm called BALANCE (Byzantine-robust averaging through local similarity in decentralization) to defend against poisoning attacks in DFL.
  arXiv  Detail & Related papers  (2024-06-14T21:28:37Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Mitigating Cross-client GANs-based Attack in Federated Learning [78.06700142712353]
  Multi distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model. FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack. We propose Fed-EDKD technique to improve the current popular FL schemes to resist C-GANs attack.
  arXiv  Detail & Related papers  (2023-07-25T08:15:55Z)
• 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)
• AFLGuard: Byzantine-robust Asynchronous Federated Learning [41.47838381772442]
  Asynchronous FL aims to enable the server to update the model once any client's model update reaches it without waiting for other clients' model updates. Asynchronous FL is also vulnerable to poisoning attacks, in which malicious clients manipulate the model via poisoning their local data and/or model updates sent to the server. We propose AFLGuard, a Byzantine-robust asynchronous FL method.
  arXiv  Detail & Related papers  (2022-12-13T02:07:58Z)
• MUDGUARD: Taming Malicious Majorities in Federated Learning using Privacy-Preserving Byzantine-Robust Clustering [34.429892915267686]
  Byzantine-robust Federated Learning (FL) aims to counter malicious clients and train an accurate global model while maintaining an extremely low attack success rate. Most existing systems, however, are only robust when most of the clients are honest. We propose a novel Byzantine-robust and privacy-preserving FL system, called MUDGUARD, that can operate under malicious minority emphor majority in both the server and client sides.
  arXiv  Detail & Related papers  (2022-08-22T09:17:58Z)
• Robust Quantity-Aware Aggregation for Federated Learning [72.59915691824624]
  Malicious clients can poison model updates and claim large quantities to amplify the impact of their model updates in the model aggregation. Existing defense methods for FL, while all handling malicious model updates, either treat all quantities benign or simply ignore/truncate the quantities of all clients. We propose a robust quantity-aware aggregation algorithm for federated learning, called FedRA, to perform the aggregation with awareness of local data quantities.
  arXiv  Detail & Related papers  (2022-05-22T15:13:23Z)
• RoFL: Attestable Robustness for Secure Federated Learning [59.63865074749391]
  Federated Learning allows a large number of clients to train a joint model without the need to share their private data. To ensure the confidentiality of the client updates, Federated Learning systems employ secure aggregation. We present RoFL, a secure Federated Learning system that improves robustness against malicious clients.
  arXiv  Detail & Related papers  (2021-07-07T15:42:49Z)

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.