Research on the Security Technology of Federated Learning Privacy Preserving

Mao, Juan; Cao, Chunjie; Wang, Longjuan; Ye, Jun; Zhong, Wenjie

doi:10.1088/1742-6596/1757/1/012192

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They aimed to provide a concise summary of the topic that can help guide the research community toward robust privacy-preserving FL system design. In contrast, Mao et al (2021) discussed security and privacy concerns in FL. The article briefly listed the major privacy-preserving techniques and suggestions for future work.…”

Section: Comparison With Other Survey Articlesmentioning

confidence: 99%

Federated learning for 6G-enabled secure communication systems: a comprehensive survey

et al. 2023

View full text Add to dashboard Cite

Machine learning (ML) and Deep learning (DL) models are popular in many areas, from business, medicine, industries, healthcare, transportation, smart cities, and many more. However, the conventional centralized training techniques may not apply to upcoming distributed applications, which require high accuracy and quick response time. It is mainly due to limited storage and performance bottleneck problems on the centralized servers during the execution of various ML and DL-based models. However, federated learning (FL) is a developing approach to training ML models in a collaborative and distributed manner. It allows the full potential exploitation of these models with unlimited data and distributed computing power. In FL, edge computing devices collaborate to train a global model on their private data and computational power without sharing their private data on the network, thereby offering privacy preservation by default. But the distributed nature of FL faces various challenges related to data heterogeneity, client mobility, scalability, and seamless data aggregation. Moreover, the communication channels, clients, and central servers are also vulnerable to attacks which may give various security threats. Thus, a structured vulnerability and risk assessment are needed to deploy FL successfully in reallife scenarios. Furthermore, the scope of FL is expanding in terms of its application areas, with each area facing different threats. In this paper, we analyze various vulnerabilities present in the FL environment and design a literature survey of possible threats from the perspective of different application areas. Also, we review the most recent defensive algorithms and strategies used to guard against security and privacy threats in those areas. For a systematic coverage of the topic, we considered various applications under four main categories: space, air, ground, and underwater communications. We also compared the proposed methodologies regarding the underlying approach, base model, datasets, evaluation matrices, and achievements. Lastly, various approaches' future directions and existing drawbacks are discussed in detail.

show abstract

Section: Comparison With Other Survey Articlesmentioning

confidence: 99%

Federated learning for 6G-enabled secure communication systems: a comprehensive survey

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the above algorithm, the ∈ is the privacy parameter and it will be a positive number, which is the output distribution algorithm is less affected by any recode in the data set [29].…”

Section: Differential Privacy Formulamentioning

confidence: 99%

“…SMC is the solution for a variety of problems of collaborative computation to use data without compromising privacy, and mush assures the con dentiality, independence, and accuracy of the information for all parties, each party only knows about their input and output, not anything else related to the process. [29]…”

Section: Secure Multiparty Computationmentioning

confidence: 99%

See 1 more Smart Citation

Security Model and Algorithms in Federate learning under IoT Critical Infrastructure

Jalali

Chen

2022

Preprint

View full text Add to dashboard Cite

in today's digital world, IoT has a vital and very important role in offering and exchanging information services throughout the internet. it is new technologies and applications that have a deep effect on every domain of our daily life such as education, social, healthcare, and so on. IoT deals with many different sensing objects and machines that interact with each other to do their activities, IoT collects and exchanges data from all sensing objects and machines. Stores the collected data in structured or unstructured format managed through cloud platform services. Due to IoT have classical centralized learning algorithms, it affects directly by computational power and time, most importantly security and privacy issues respect with to user data. So for overcoming these challenges, federated learning is a favorable solution that enables on-object machine learning without migrating end-user private data to the central point (cloud), as well as Artificial Intelligent (AI) benefits to domains with sensitive data, only learning model update will be transferred between end-devices and the central server. By using the federated learning model the scope of the decentralized approach will be boost by having a huge number of clients for collaborating training, this FL makes vulnerable again various security threats and risks. In this paper, we analyze the overall vulnerabilities being exploited by malicious attackers which impact system security and privacy violation, common security threats and attacks in FL to distributed machine learning solutions and defensive techniques to enhance security/privacy vulnerabilities such as security models and algorithms to secure information in a decentralized system, network security as well as access control for availability, integrity, and confidentiality ( AIC), end device are required to protect and secured from unauthorized access.

show abstract

“…In the framework, data is usually achieved by adding noise to the updated parameters to prevent curious participants from inferring training data. The technology is called differential privacy [6]. There are several proposed differentially private mechanisms.…”

Section: Introductionmentioning

confidence: 99%

A None-zero Mean Noise Adding Mechanism in Differential Privacy in Federated Learning of Neural Networks Based on Fully Homomorphic Encryption and Greedy Average Block Kaczmarz

Wang

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Scholars propose a noise adding mechanism in local differential privacy to provide a strict privacy guarantee to federated learning. However, there are two problems. On the one hand, the noisy data is close to its original value with high probability due to the zero mean random noise, leading to the information exposure. On the other hand, a large variance of the noise makes the estimated average of the parameters bias. To overcome the difficulties, we propose a framework of none-zero mean noise adding mechanism in differential privacy in federated learning of deep networks based on fully homomorphic encryption and greedy average block Kaczmarz method. In the work, a none-zero mean adding noise to original data is determined locally according to the correlation between the local and global distributions. Using fully homomorphic encryption and greedy average block Kaczmarz method, a de-noising weighting aggregation strategy is derived without decryption of the mean to guarantee the privacy of user by a third party. Moreover, the weight is generated complete randomly so that it is difficult to obtain the mean. As the means are different among the clients and unpredictable for attackers, the variance of the noise can be small. Experiments show that the proposed method provides a higher level of accuracy than the non-privacy-preserving federated learning, while it guarantee privacy for multi-party machine learning tasks.

show abstract

Research on the Security Technology of Federated Learning Privacy Preserving

Cited by 6 publications

References 7 publications

Federated learning for 6G-enabled secure communication systems: a comprehensive survey

Federated learning for 6G-enabled secure communication systems: a comprehensive survey

Security Model and Algorithms in Federate learning under IoT Critical Infrastructure

A None-zero Mean Noise Adding Mechanism in Differential Privacy in Federated Learning of Neural Networks Based on Fully Homomorphic Encryption and Greedy Average Block Kaczmarz

Contact Info

Product

Resources

About