Data Quality Detection Mechanism Against Label Flipping Attacks in Federated Learning

Jiang, Yifeng; Zhang, Weiwen; Chen, Yanxi

doi:10.1109/tifs.2023.3249568

Cited by 17 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MNIST is one of the most popular datasets in the field of machine learning, consisting of 60000 hand-written digital images with a size of 28*28, labeled 0-9; KDDCup is a dataset used to evaluate intrusion detection algorithms, and its training set consists of 23 types of data and the data distribution of different types is imbalanced, which can effectively test the robustness of our proposed method under non-IID data. In the experiment, we make the attack nodes of sybil attacks initiate label flipping attacks [16].…”

Section: Methodsmentioning

confidence: 99%

Sybil attacks detection for dynamic environment in federated learning

Lin,

Zhu,

Wang

2024

Fourth International Conference on Telecommunications, Optics, and Computer Science (TOCS 2023)

View full text Add to dashboard Cite

Federated learning can utilize its distributed structure to protect data privacy security of clients and improve efficiency of machine learning. However, its distributed framework also make itself be susceptible to sybil attacks. While previous research has already proposed defense methods to address this issue, they often fail to guarantee effective performance in a dynamic federated learning system, where some clients dynamically join in and out. To tackle this problem, our paper introduces a novel defense method specifically designed to mitigate sybil attacks in dynamic federated learning scenario. Our proposed method consists of three mechanisms: similarity mechanism, validation mechanism, and reputation mechanism. These mechanisms can address the problem of missing information and effectively resist sybil attacks in dynamic federated learning. We evaluate the performance of our method on the MNIST and KDDCup datasets and demonstrate its advanced ability in defending against sybil attacks in dynamic federated learning compared to existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Sybil attacks detection for dynamic environment in federated learning

Lin,

Zhu,

Wang

2024

Fourth International Conference on Telecommunications, Optics, and Computer Science (TOCS 2023)

View full text Add to dashboard Cite

show abstract

“…Ensuring the long-term functionality of the system and guaranteeing data quality and fair payment during cooperation are crucial. Jiang et al [27] proposed a malicious client-detection federated-learning mechanism (MCDFL) facing labelflipping attacks, which, in a 6G environment, more efficiently detects the data quality of each client by recovering the distribution of latent feature spaces. Li et al [28] proposed an incentive mechanism based on contract theory.…”

Section: Data Security Issues Arising In 6g Networkmentioning

confidence: 99%

A Data Attack Detection Framework for Cryptography-Based Secure Aggregation Methods in 6G Intelligent Applications

Sun,

Liang,

Yin

et al. 2024

Electronics

View full text Add to dashboard Cite

Eagerly anticipated, 6G networks are attributed with a variety of characteristics by researchers. A pivotal characteristic of 6G networks is the deep integration of sensing and networking, along with intelligent network applications operating on top of this infrastructure. To optimally harness the data collected by sensors distributed across various locations, the training paradigm of the new generation of 6G intelligence applications aligns naturally with the federated-learning paradigm. The exposure of gradients in federated learning to inversion attacks is a critical concern. To address this, cryptography-based secure aggregation methods are commonly implemented to protect the privacy and confidentiality of gradients. However, the semantic meaninglessness of encrypted data makes it difficult to assess the correctness, availability, and source legitimacy of participants’ data. In this paper, we propose a data attack detection framework for cryptography-based secure aggregation methods in 6G intelligence applications that address the security vulnerabilities associated with encrypted data obscurity. We employ a suite of encrypted-data-auditing techniques to prevent data-aggregation errors, data poisoning, and illegal data sources. Additionally, we have compared a series of promising security methods, analyzed, and provided recommendations for the most suitable security approaches in specific 6G scenarios.

show abstract

“…In this paper, we mainly focus on three types of representative poisoning attacks: (1) Label-flipping attack [6](data poisoning). In a data set, each data sample carries a category label.…”

Section: Introductionmentioning

confidence: 99%

MS-FL: A Federated Learning Framework Based on Multiple Security Strategies

Yang,

Kang,

Wei

2024

IEEE Access

View full text Add to dashboard Cite

With the establishment and standardization of the data trading market, an increasing number of users are utilizing multi-party data for federated machine learning to obtain their desired models. Therefore, scholars have proposed numerous federated learning frameworks to address practical issues. However, there are still three issues that need to be addressed in current federated learning frameworks: 1) privacy protection, 2) poisoning attack, and 3) protection of the interests of participants. To address these issues, this paper proposes a novel federated learning framework MS-FL based on multiple security strategies. The framework's algorithms guarantee that data providers need not worry about data privacy leakage. At the same time, it can defend against poisoning attack from malicious nodes. Finally, to ensure the interests of all parties are protected, a blockchain protocol is utilized. The theoretical derivation proves the effectiveness of this framework. Experimental results show that the algorithm designed in this paper outperforms other algorithms.

show abstract

Data Quality Detection Mechanism Against Label Flipping Attacks in Federated Learning

Cited by 17 publications

References 27 publications

Sybil attacks detection for dynamic environment in federated learning

Sybil attacks detection for dynamic environment in federated learning

A Data Attack Detection Framework for Cryptography-Based Secure Aggregation Methods in 6G Intelligent Applications

MS-FL: A Federated Learning Framework Based on Multiple Security Strategies

Contact Info

Product

Resources

About