Search

Self-supervised learning in the federated learning paradigm has been gaining a lot of interest both in industry and research due to the collaborative learning capability on unlabeled yet isolated data. However, self-supervised based federated learning strategies suffer from performance degradation due to label scarcity and diverse data distributions, i.e., data heterogeneity. In this paper, we propose the SelfFed framework for medical images to overcome data heterogeneity and label scarcity issues. The first phase of the SelfFed framework helps to overcome the data heterogeneity issue by leveraging the pre-training paradigm that performs augmentative modeling using Swin Transformer-based encoder in a decentralized manner. The label scarcity issue is addressed by fine-tuning paradigm that introduces a contrastive network and a novel aggregation strategy. We perform our experimental analysis on publicly available medical imaging datasets to show that SelfFed performs better when compared to existing baselines and works. Our method achieves a maximum improvement of 8.8% and 4.1% on Retina and COVID-FL datasets on non-IID datasets. Further, our proposed method outperforms existing baselines even when trained on a few (10%) labeled instances. [ABSTRACT FROM AUTHOR]

Cybersecurity assessments are critical for ensuring that security measures in organizational infrastructures, systems, and applications meet necessary requirements. Given the significant HTTPS vulnerabilities exposed in recent years, assessing HTTPS deployments is increasingly important. However, there has been no systematic literature review (SLR) comparing different cybersecurity assessment methods specifically for HTTPS deployment security issues. This study aims to address this gap by identifying, analyzing, and comparing various HTTPS deployment assessment methods documented in scientific literature. Our approach involved a structured research methodology with specific inclusion and exclusion criteria for selecting relevant methods. The review utilizes 16 comparison metrics, divided into two categories: critical security metrics, focusing on assessment metrics adopted and the number of vulnerabilities evaluated by each method, and additional metrics assessing the methods' applicability and effectiveness in real-world scenarios. The findings indicate varied adoption rates of these metrics among the reviewed cybersecurity assessment methods, highlighting the absence of a standardized approach using common, well-defined security metrics for HTTPS deployment assessment. In contrast, merging all the comparison metrics outlined in this review would enable a more in-depth assessment of HTTPS deployment security issues, enhance the quality of reported results, and lead to the development of a more practical assessment method. • A collection of reviews on cybersecurity and risk assessment methods was identified. • 24 cybersecurity assessment methods for HTTPS deployment were carefully selected. • 16 comparison metrics categorized into security and applicability were analyzed. • The practical effectiveness of selected methods in real-world scenarios was assessed. • Lessons and research questions are highlighted after comparing the chosen methods. [ABSTRACT FROM AUTHOR]