Non-interactive, Secure Verifiable Aggregation for Decentralized, Privacy-Preserving Learning

Brunetta, Carlo; Tsaloli, Georgia; Liang, Bei; Banegas, Gustavo; Mitrokotsa, Aikaterini

doi:10.1007/978-3-030-90567-5_26

Cited by 12 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Fastsecagg [147], by sacrificing some security, the authors substitute the standard Shamir secret sharing with a more efficient FFT-based multisecret sharing scheme. Alternatively, models can be shared between two servers as in [148], [149], [150], [151], or several servers such as [152], [153]. Some other works introduce a two-phase secret-sharing-based aggregation [154], [155].…”

Section: Mpc-based Aggregationmentioning

confidence: 99%

“…Then in the second phase, all users share their models to the users in the committee for aggregation relying on standard MPC protocols that are similar to the aforementioned works. Furthermore, to guarantee the correctness of the aggregation result with a malicious central server, verifiable secret sharing schemes are adopted in [153], [156]. Share data.…”

Section: Mpc-based Aggregationmentioning

confidence: 99%

“…If these users are set to be honest users, the proposed protocol will allow the verification of the computation results. For example, [153], [156] acknowledge the verification on the correctness of the aggregation result only when a set of users of which the number is greater than the threshold have verified the result. However, we should note that the setting of threshold value leads to a trade-off depending on its usage.…”

Section: Mpc-based Aggregationmentioning

confidence: 99%

See 2 more Smart Citations

Privacy-Preserving Aggregation in Federated Learning: A Survey

Liu¹,

Guo²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Over the recent years, with the increasing adoption of Federated Learning (FL) algorithms and growing concerns over personal data privacy, Privacy-Preserving Federated Learning (PPFL) has attracted tremendous attention from both academia and industry. Practical PPFL typically allows multiple participants to individually train their machine learning models, which are then aggregated to construct a global model in a privacy-preserving manner. As such, Privacy-Preserving Aggregation (PPAgg) as the key protocol in PPFL has received substantial research interest. This survey aims to fill the gap between a large number of studies on PPFL, where PPAgg is adopted to provide a privacy guarantee, and the lack of a comprehensive survey on the PPAgg protocols applied in FL systems. In this survey, we review the PPAgg protocols proposed to address privacy and security issues in FL systems. The focus is placed on the construction of PPAgg protocols with an extensive analysis of the advantages and disadvantages of these selected PPAgg protocols and solutions. Additionally, we discuss the open-source FL frameworks that support PPAgg. Finally, we highlight important challenges and future research directions for applying PPAgg to FL systems and the combination of PPAgg with other technologies for further security improvement.

show abstract

Section: Mpc-based Aggregationmentioning

confidence: 99%

Section: Mpc-based Aggregationmentioning

confidence: 99%

Section: Mpc-based Aggregationmentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Aggregation in Federated Learning: A Survey

Liu¹,

Guo²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We consider an example with v = 1, E = 4, H = 6, T h = 2, s = 1, and T c = 2. Each Client i ∈ [4] Server Client (a) Messages table…”

Section: Secure Aggregation Scheme a Lagrange Coding With Mask (Lcm)mentioning

confidence: 99%

Two-layer Coded Gradient Aggregation with Straggling Communication Links

Liang

2021

2020 IEEE Information Theory Workshop (ITW)

View full text Add to dashboard Cite

In many distributed learning setups such as federated learning (FL), client nodes at the edge use individually collected data to compute local gradients and send them to a central master server. The master server then aggregates the received gradients and broadcasts the aggregation to all clients, with which the clients can update the global model. In this paper, we consider multi-server federated learning with secure aggregation and unreliable communication links. We first define a threat model using Shannon's information-theoretic security framework, and propose a novel scheme called Lagrange Coding with Mask (LCM), which divides the servers into groups and uses Coding and Masking techniques. LCM can achieve a tradeoff between the uplink and downlink communication loads by adjusting the number of servers in each group. Furthermore, we derive the lower bounds of the uplink and downlink communication loads, respectively, and prove that LCM achieves the optimal uplink communication load, which is unrelated to the number of collusion clients.

show abstract

“…We refer the reader to [16,17] for more MPC libraries and the comparison of known libraries. Many applications can be built upon MPC to protect the privacy of data, including machine learning (see, e.g., [18][19][20][21][22][23][24][25][26][27][28][29][30][31] and references therein), federated learning (see, e.g., [32][33][34][35][36]), data mining [37][38][39][40], auction [41][42][43], genomic analysis [44][45][46], securing databases (see [47] and references therein), and blockchain [48][49][50][51][52][53]. In addition, some techniques underlying MPC protocols can also be used to construct non-interactive zero-knowledge (ZK) proofs [54][55][56][57][58][59][60][61] based on the MPC-in-thehead paradigm, scalable ZK proofs…”

Section: Introductionmentioning

confidence: 99%

Concretely efficient secure multi-party computation protocols: survey and more

Feng

Yang

2022

Security and Safety

View full text Add to dashboard Cite

Secure multi-party computation (MPC) allows a set of parties to jointly compute a function on their private inputs, and reveals nothing but the output of the function. In the last decade, MPC has rapidly moved from a purely theoretical study to an object of practical interest, with a growing interest in practical applications such as privacy-preserving machine learning (PPML). In this paper, we comprehensively survey existing work on concretely efficient MPC protocols with both semi-honest and malicious security, in both dishonest-majority and honest-majority settings. We focus on considering the notion of security with abort, meaning that corrupted parties could prevent honest parties from receiving output after they receive output. We present high-level ideas of the basic and key approaches for designing different styles of MPC protocols and the crucial building blocks of MPC. For MPC applications, we compare the known PPML protocols built on MPC, and describe the efficiency of private inference and training for the state-of-the-art PPML protocols. Furthermore, we summarize several challenges and open problems to break though the efficiency of MPC protocols as well as some interesting future work that is worth being addressed. This survey aims to provide the recent development and key approaches of MPC to researchers, who are interested in knowing, improving, and applying concretely efficient MPC protocols.

show abstract

Non-interactive, Secure Verifiable Aggregation for Decentralized, Privacy-Preserving Learning

Cited by 12 publications

References 30 publications

Privacy-Preserving Aggregation in Federated Learning: A Survey

Privacy-Preserving Aggregation in Federated Learning: A Survey

Two-layer Coded Gradient Aggregation with Straggling Communication Links

Concretely efficient secure multi-party computation protocols: survey and more

Contact Info

Product

Resources

About