Efficient Secure Building Blocks With Application to Privacy Preserving Machine Learning Algorithms

Kjamilji, Artrim; Savaş, Erkay; Lévi, Albert

doi:10.1109/access.2021.3049216

Cited by 15 publications

(4 citation statements)

References 43 publications

(105 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To accommodate data owners' constant need for secure and collaborative data execution, an FL environment provides guarantees and assurances from a privacy and security perspective. However, the literature pinpoints other diverse scenarios that emphasize privacy, for example, during model-training [55] and also during security-based model training [56].…”

Section: Data Privacy and Security Threatsmentioning

confidence: 99%

See 1 more Smart Citation

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

Alawadi,

Alkharabsheh,

Alkhabbas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model's highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers.

show abstract

Section: Data Privacy and Security Threatsmentioning

confidence: 99%

“…Traditional methods inadvertently raise significant privacy concerns when sharing such code repositories or data with external parties. This study assesses these capabilities from the perspective of intentional or unintentional data leakage, which could compromise the trained model [56].…”

Section: Data Privacy and Security Threatsmentioning

confidence: 99%

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

Alawadi,

Alkharabsheh,

Alkhabbas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Fully Homomorphic Encryption (FHE) makes the machine learning training process easier without data leakage. Deep learning and shallow machine learning algorithms heavily rely on domain data, which are often difficult to share publicly [176]. FHE has facilitated a new process to delegate these kinds of sensitive data sharing without sharing the actual meaningful data.…”

Section: Homomorphic Encryptionmentioning

confidence: 99%

Cybersecurity Threats and Their Mitigation Approaches Using Machine Learning—A Review

Ahsan

Nygard

Gomes

et al. 2022

JCP

View full text Add to dashboard Cite

Machine learning is of rising importance in cybersecurity. The primary objective of applying machine learning in cybersecurity is to make the process of malware detection more actionable, scalable and effective than traditional approaches, which require human intervention. The cybersecurity domain involves machine learning challenges that require efficient methodical and theoretical handling. Several machine learning and statistical methods, such as deep learning, support vector machines and Bayesian classification, among others, have proven effective in mitigating cyber-attacks. The detection of hidden trends and insights from network data and building of a corresponding data-driven machine learning model to prevent these attacks is vital to design intelligent security systems. In this survey, the focus is on the machine learning techniques that have been implemented on cybersecurity data to make these systems secure. Existing cybersecurity threats and how machine learning techniques have been used to mitigate these threats have been discussed. The shortcomings of these state-of-the-art models and how attack patterns have evolved over the past decade have also been presented. Our goal is to assess how effective these machine learning techniques are against the ever-increasing threat of malware that plagues our online community.

show abstract

“…Other scientists, based on panel data illustrated that financial development is unfavourable to economic development, but this negative effect is stronger in the countries with high level of income (Cheng et al, 2021). In these conditions, block-chain technology and computer-based education improve cyber defence (Kjamilji et al, 2021). Such models allow digitalizing client service through creation of self-learning models too.…”

Section: Literature Reviewmentioning

confidence: 99%

Impact of financial technologies on economic development: Theories, methods and analysis

Kireyeva¹,

Kredina²,

Vasa³

et al. 2021

Journal of International Studies

View full text Add to dashboard Cite

This research focuses on an analytical review of the scientific literature to select appropriate methods and evaluate the impact of financial technologies on economic growth. Since non-cash payments can be affected by various factors, there is a great variety of studies relating to them in the scientific literature. However, existing scientific papers reflecting on the economic growth and noncash payments do not determine the cause-effect relationship trends in different periods. Current study intends to fill this gap. Using an original method based on correlation analysis, the relationship of indicators in different periods is calculated with the use of the SPSS software. The data is collected for period of 2004-2019, during which the reviewed countries were actively developing and increasing their financial and technological capacities. Analysis results largely indicate an increase in the number of bank branches in many of the reviewed countries. Further, we

show abstract

Efficient Secure Building Blocks With Application to Privacy Preserving Machine Learning Algorithms

Cited by 15 publications

References 43 publications

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

Cybersecurity Threats and Their Mitigation Approaches Using Machine Learning—A Review

Impact of financial technologies on economic development: Theories, methods and analysis

Contact Info

Product

Resources

About