Research Output
Articles
Publication Date: 2025
Journal of Information Security and Applications (22142126)89
The widespread availability of DNA sequencing technology has led to the genetic sequences of individuals becoming accessible data, creating opportunities to identify the genetic factors underlying various diseases. In particular, Genome-Wide Association Studies (GWAS) seek to identify Single Nucleotide Polymorphism (SNPs) associated with a specific phenotype. Although sharing such data offers valuable insights, it poses a significant challenge due to both privacy concerns and the large size of the data involved. To address these challenges, in this paper, we propose a novel framework that combines both federated learning and blockchain as a platform for conducting GWAS studies with the participation of single individuals. The proposed framework offers a mutually beneficial solution where individuals participating in the GWAS study receive insurance credit to avail medical services while research and treatment centers benefit from the study data. To safeguard model parameters and prevent inference attacks, a secure aggregation protocol has been developed. The evaluation results demonstrate the scalability and efficiency of the proposed framework in terms of runtime and communication, outperforming existing solutions. © 2025
Publication Date: 2025
Expert Systems with Applications (09574174)262
Generative Adversarial Networks (GANs) do not ensure the privacy of the training datasets and may memorize sensitive details. To maintain privacy of data during inference, various privacy-preserving GAN mechanisms have been proposed. Despite the different approaches and their characteristics, advantages, and disadvantages, there is a lack of a systematic review on them. This paper first presents a comprehensive survey on privacy-preserving mechanisms and offers a taxonomy based on their characteristics. The survey reveals that many of these mechanisms modify the GAN learning algorithm to enhance privacy, highlighting the need for theoretical and empirical analysis of the impact of these modifications on GAN convergence. Among the surveyed methods, ADAM-DPGAN is a promising approach that ensures differential privacy in GANs for both the discriminator and the generator networks when using the ADAM optimizer, by introducing appropriate noise based on the global sensitivity of discriminator parameters. Therefore, this paper conducts a theoretical and empirical analysis of the convergence of ADAM-DPGAN. In the presented theoretical analysis, assuming that simultaneous/alternating gradient descent method with ADAM optimizer converges locally to a fixed point and its operator is L-Lipschitz with L < 1, the effect of ADAM-DPGAN-based noise disturbance on local convergence is investigated and an upper bound for the convergence rate is provided. The analysis highlights the significant impact of differential privacy parameters, the number of training iterations, the discriminator's learning rate, and the ADAM hyper-parameters on the convergence rate. The theoretical analysis is further validated through empirical analysis. Both theoretical and empirical analyses reveal that a stronger privacy guarantee leads to a slower convergence, highlighting the trade-off between privacy and performance. The findings also indicate that there exists an optimal value for the number of training iterations regarding the privacy needs. The optimal settings for each parameter are calculated and outlined in the paper. © 2024 Elsevier Ltd
Publication Date: 2025
Journal of Supercomputing (15730484)81(1)
With the fast development of cloud computing, clients without enough computational power can widely outsource their heavy computations to cloud service providers. One of the most widely used and costly operations in cryptographic protocols is modular exponentiation, which can be computed at a lower cost by enjoying advantages of cloud computing, however, at the same time we need to address new challenges such as data privacy and verification of results. In this paper, first, we propose a secure outsourcing of single modular exponentiation protocol with verifiability one. Although the proposed single exponentiation scheme has the same verifiability as Ren’2018, but our scheme requires one less modular multiplication. However, the main contribution of this paper is proposing a scheme for outsourcing of multiplications of several modular exponentiations, hereafter called as composite exponentiation, which to the best of our knowledge, and is the first outsourcing scheme with full verification for composite exponentiation. As the evaluation results show, the advantages of this scheme, in comparison with state of the art schemes, are evident in terms of performance and verifiability criteria. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
