Cryptographic algorithms for privacy-preserving online applications

Li, Ruinian; Xiao, Yinhao; Zhang, Cheng; Song, Tianyi; Hu, Chunqiang

doi:10.3934/mfc.2018015

Cited by 13 publications

(5 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formally, n number of clients {P 1 , P 2 , … , P n } want to calculate a global function f {I 1 , I 2 , … , I n } from their individual dataset I i . A protocol is considered SMPC if it ensures (Li et al 2018): (i) the function f {I 1 , I 2 , … , I n } is accurate, and (2) no private information of I n is disclosed to other participants. To improve the privacy of FL, SMPC is frequently used.…”

Section: Secure Multi-party Computation-based Approachmentioning

confidence: 99%

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

Saha,

Hota,

Chattopadhyay

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Federated learning (FL) refers to a system of training and stabilizing local machine learning models at the global level by aggregating the learning gradients of the models. It reduces the concern of sharing the private data of participating entities for statistical analysis to be carried out at the server. It allows participating entities called clients or users to infer useful information from their raw data. As a consequence, the need to share their confidential information with any other entity or the central entity called server is eliminated. FL can be clearly interpreted as a privacy-preserving version of traditional machine learning and deep learning algorithms. However, despite this being an efficient distributed training scheme, the client’s sensitive information can still be exposed to various security threats from the shared parameters. Since data has always been a major priority for any user or organization, this article is primarily concerned with discussing the significant problems and issues relevant to the preservation of data privacy and the viability and feasibility of several proposed solutions in the FL context. In this work, we conduct a detailed study on FL, the categorization of FL, the challenges of FL, and various attacks that can be executed to disclose the users’ sensitive data used during learning. In this survey, we review and compare different privacy solutions for FL to prevent data leakage and discuss secret sharing (SS)-based security solutions for FL proposed by various researchers in concise form. We also briefly discuss quantum federated learning (QFL) and privacy-preservation techniques in QFL. In addition to these, a comparison and contrast of several survey works on FL is included in this work. We highlight the major applications based on FL. We discuss certain future directions pertaining to the open issues in the field of FL and finally conclude our work.

show abstract

Section: Secure Multi-party Computation-based Approachmentioning

confidence: 99%

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

Saha,

Hota,

Chattopadhyay

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…Homomorphic encryption [148] is a form of encryption. Formally, an encryption algorithm En is called homomorphic over an operator if fulfilling the criterion En(m 1 ) En(m 2 ) = En(m 1 m 2 ), ∀m 1 , m 2 ∈ M, where M denotes a set of plaintext [98]. According to the supported operators, homomorphic encryption methods can be divided into two categories: partially homomorphic encryption [134] and fully homomorphic encryption [176].…”

Section: Cryptographic Techniquesmentioning

confidence: 99%

“…Formally, a dealer distributes a secret s to n participants, each of whom is allocated one share. Then, the (t, n)-threshold secret sharing is defined by fulfilling the following criteria [98]: (1) For an arbitrary subset of m participants with m t, the secret s can be reconstructed from m shares, and (2) for an arbitrary subset of m participants with m < t, the secret s cannot be reconstructed from m shares. The methods proposed in References [12,156] are two widely used (t, n)-threshold secret sharing methods.…”

Section: Cryptographic Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey of Privacy-preserving Federated Learning

2021

View full text Add to dashboard Cite

The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) has been heralded as a solution to generic privacy-preserving machine learning. However, the challenge of protecting data privacy while maintaining the data utility through machine learning still remains. In this article, we present a comprehensive and systematic survey on the PPFL based on our proposed 5W-scenario-based taxonomy. We analyze the privacy leakage risks in the FL from five aspects, summarize existing methods, and identify future research directions.

show abstract

“…For the privacy protection of the query content, the asymmetric key encryption algorithm of RSA(Rivest-Shamir-Adleman) is adopted through the research and study of the secure multi-party computing model (Li et al, 2018). Through the combination of the two methods, a better privacy protection effect is achieved.…”

mentioning

confidence: 99%

Trusted Computing and Privacy Protection of Computer Internet of Things Nodes Based on Deep Fuzzy Control of Dynamic Learning Rate

Sun,

Pezzola

2024

International Journal of Fuzzy System Applications

View full text Add to dashboard Cite

Under the background of mobile Internet of Things, this paper focuses on the solutions of trusted computing and privacy protection of Internet of Things nodes. Based on the research of existing mainstream service discovery protocols and the deep fuzzy control theory of dynamic learning rate, this paper proposes a trusted computing algorithm for Internet of Things nodes in mobile Internet of Things,which takes into account service quality and user preference.This paper combines the depth fuzzy control model of IoT nodes proposed before, uses a normal data set to train it, and then makes it generate and play the prediction residuals. It will be further used to build a privacy protection model and realize the anomaly detection of privacy protection data in the Internet of Things. This paper designs and implements a trusted computing system using the Internet of Things platform,which has been tested. Experimental results show that, compared with previous elastic matching algorithms, the precision and recall of the new algorithm proposed in this paper are improved.

show abstract

Cryptographic algorithms for privacy-preserving online applications

Cited by 13 publications

References 65 publications

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

A Comprehensive Survey of Privacy-preserving Federated Learning

Trusted Computing and Privacy Protection of Computer Internet of Things Nodes Based on Deep Fuzzy Control of Dynamic Learning Rate

Contact Info

Product

Resources

About