Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions

Xu, Ran; Joshi, James

doi:10.48550/arxiv.2011.06191

Cited by 2 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach in [22] employs the threshold Paillier cryptosystem to perform multi-party secure aggregation, while HybridAlpha [24] uses a functional encryption cryptosystem to securely aggregate encrypted local models. Existing secure aggregation approaches mainly follow three directions: pairwise masking based approach [3,9], homomorphic encryption based approach [18,22,15] and functional encryption [24,25,27,26,23].…”

Section: Related Workmentioning

confidence: 99%

DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting

Xu¹,

Baracaldo²,

Zhou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Federated learning has emerged as a privacy-preserving machine learning approach where multiple parties can train a single model without sharing their raw training data. Federated learning typically requires the utilization of multi-party computation techniques to provide strong privacy guarantees by ensuring that an untrusted or curious aggregator cannot obtain isolated replies from parties involved in the training process, thereby preventing potential inference attacks. Until recently, it was thought that some of these secure aggregation techniques were sufficient to fully protect against inference attacks coming from a curious aggregator. However, recent research has demonstrated that a curious aggregator can successfully launch a disaggregation attack to learn information about model updates of a target party. This paper presents DeTrust-FL, an efficient privacy-preserving federated learning framework for addressing the lack of transparency that enables isolation attacks, such as disaggregation attacks, during secure aggregation by assuring that parties' model updates are included in the aggregated model in a private and secure manner. DeTrust-FL proposes a decentralized trust consensus mechanism and incorporates a recently proposed decentralized functional encryption scheme in which all parties agree on a participation matrix before collaboratively generating decryption key fragments, thereby gaining control and trust over the secure aggregation process in a decentralized setting. Our experimental evaluation demonstrates that DeTrust-FL outperforms state-of-the-art FE-based secure multi-party aggregation solutions in terms of training time and reduces the volume of data transferred. In contrast to existing approaches, this is achieved without creating any trust dependency on external trusted entities.

show abstract

Section: Related Workmentioning

confidence: 99%

DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting

Xu¹,

Baracaldo²,

Zhou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides, except for most recently proposed decentralized FE schemes [162,74,163], the classic FE schemes are relied on a trusted third-party authority to provide key services, such as issuing a functional private key associated with specific functionalities. We refer the reader to [164] for a comprehensive study of unique characteristics using emerging and promising functional encryption techniques for various secure computation tasks.…”

Section: Modern Cryptographic Approachesmentioning

confidence: 99%

“…Specifically, even though the crypto community tries to propose various types of homomorphic-or functional-encryption schemes that may focus on providing formal security proof, increasing the security degree, or supporting more generic functionality, there is still a lack of efforts to construct a simple, practical, functionality-specific encryption schemes. We refer the reader to [164] for a comprehensive study of challenges and directions using emerging and promising functional encryption techniques for the secure computation problem. Especially when meeting the edge computing scenario wherein the IoT sensors or mobile devices have limited computation capability; such a demand is emergent in the crypto-based PPML system.…”

Section: Computation Efficiency Improvementmentioning

confidence: 99%

Privacy-Preserving Machine Learning: Methods, Challenges and Directions

Xu¹,

Baracaldo²,

Joshi

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) is increasingly being adopted in a wide variety of application domains. Usually, a well-performing ML model, especially, emerging deep neural network model, relies on a large volume of training data and high-powered computational resources. The need for a vast volume of available data raises serious privacy concerns because of the risk of leakage of highly privacy-sensitive information and the evolving regulatory environments that increasingly restrict access to and use of privacy-sensitive data. Furthermore, a trained ML model may also be vulnerable to adversarial attacks such as membership/property inference attacks and model inversion attacks. Hence, well-designed privacy-preserving ML (PPML) solutions are crucial and have attracted increasing research interest from academia and industry. More and more efforts of PPML are proposed via integrating privacy-preserving techniques into ML algorithms, fusing privacy-preserving approaches into ML pipeline, or designing various privacy-preserving architectures for existing ML systems. In particular, existing PPML arts cross-cut ML, system, security, and privacy; hence, there is a critical need to understand state-of-art studies, related challenges, and a roadmap for future research. This paper systematically reviews and summarizes existing privacy-preserving approaches and proposes a PGU model to guide evaluation for various PPML solutions through elaborately decomposing their privacy-preserving functionalities. The PGU model is designed as the triad of Phase, Guarantee, and technical Utility. Furthermore, we also discuss the unique characteristics and challenges of PPML and outline possible directions of future work that benefit a wide range of research communities among ML, distributed systems, security, and privacy areas.

show abstract

Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions

Cited by 2 publications

References 51 publications

DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting

DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting

Privacy-Preserving Machine Learning: Methods, Challenges and Directions

Contact Info

Product

Resources

About