FRAMH: A Federated Learning Risk-Based Authorization Middleware for Healthcare

Mazzocca, Carlo; Romandini, Nicolo; Colajanni, Michele; Montanari, Rebecca

doi:10.1109/tcss.2022.3210372

Cited by 8 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, through the consensus protocol, the blockchain can guarantee that the final global model will be created without any kind of bias. This trend is also corroborated by many recent works [4]- [7] that have enriched FL with blockchain for different purposes such as accountability, data provenance, or improving trustworthiness among unknown participants. Despite the full-blown benefits of using blockchain, its widespread adoption is often inhibited by energy consumption which is one of the significant concerns also due to the current discussions on climate change and sustainability [8].…”

Section: Introductionsupporting

confidence: 55%

“…However, since the overall power consumption is lower than 3W, it can be deployed in real-world scenarios. For example, a client connector can be deployed on a Jatson Nano 4 since it provides satisfying compute performance with 5-10W of power consumption. V. CONCLUSIONS AND FUTURE WORK The interest in integrating FL and blockchain has increased remarkably over the last few years due to the blockchain's ability to address most of the weaknesses of using of a central parameter server and enhance trust among unknown participants, which are major barriers that hinder the widespread use of FL.…”

Section: B Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning Meets Blockchain: a Power Consumption Case Study

Romandini

Mazzocca

Montanari

2023

2023 31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

Self Cite

View full text Add to dashboard Cite

Federated learning (FL) is emerging as the most promising approach to collaboratively train a machine learning (ML) model on a common task without centralizing data. During each FL round, participants locally train a partial model with its on-premises data. Such models are subsequently aggregated to derive a global one. How these partial models are combined is a primary concern. Traditional approaches usually rely on a parameter server that introduces many weaknesses such as single point of failure, lack of trustworthiness among unknown participants, and incapacity to handle the traffic generated from millions of devices.Thus, to overcome such concerns, blockchain has recently been proposed as a valuable solution to improve the robustness of FL approaches. The full-blown benefits of using blockchain enable tackling the limits of centralized servers. However, energy consumption is still one of the significant factors inhibiting its widespread due to the current discussions on climate change and sustainability. Recently, a growing number of research works have been focusing on integrating FL and blockchain, nevertheless, adequate analysis and estimate of their energy and power consumption are often lacking.This paper presents an estimate of the power consumption of FlowChain, an architecture that integrates FL with blockchain to simplify the use of FL. Experimental results demonstrate that the overall power consumption significantly depends on the ML model adopted.

show abstract

Section: Introductionsupporting

confidence: 55%

Section: B Resultsmentioning

confidence: 99%

Federated Learning Meets Blockchain: a Power Consumption Case Study

Romandini

Mazzocca

Montanari

2023

2023 31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This would enable healthcare systems to respond quickly to new data or changing health trends, making FL models more adaptive and responsive. • Use in Remote and Real-Time Monitoring: With the proliferation of wearable devices and IoT in healthcare, FL is poised to play a significant role in real-time patient monitoring and remote healthcare, providing personalized insights and treatments based on data collected from diverse patient populations [409]. • Edge Computing Integration: Integrating FL with edge computing could decentralize the computational workload, allowing for faster and more efficient model training and updates, especially in real-time applications [406], [410], [411].…”

Section: E1 Current Trends In Fl For Healthcarementioning

confidence: 99%