DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning

Lin, Yijing; Gao, Zhipeng; Du, Hongyang; Kang, Jiawen; Niyato, Dusit; Wang, Qian; Ruan, Jingqing; Wan, Shaohua

doi:10.1109/tcomm.2023.3288591

Cited by 10 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The IoV has a significant potential to reduce carbon emissions by optimizing transportation efficiency. Through IoV's interconnectedness that can be secured using blockchain technology, vehicles can access real‐time traffic data, leading to smoother routes and reduced idling time, thus minimizing fuel consumption and emissions 40–43 . Additionally, IoV enables intelligent traffic management, promoting better traffic flow and decreased congestion, further contributing to lower carbon emissions by reducing the time vehicles spend in traffic jams.…”

Section: Carbon Tradingmentioning

confidence: 99%

Towards the net zero carbon future: A review of blockchain‐enabled peer‐to‐peer carbon trading

Parhamfar,

Sadeghkhani,

Adeli

2024

Energy Science & Engineering

View full text Add to dashboard Cite

The increasing trend of energy generation and management systems towards decentralized structures such as using renewable energy resources makes it necessary to use digital and smart platforms for exchanging information and even conducting financial transactions in a decentralized manner, known as the peer‐to‐peer model. The decentralized transaction verification of cryptocurrencies makes it possible to use these encrypted currencies and decentralized blockchain networks in energy management systems and carry out financial transactions related to carbon trading. Carbon and other greenhouse gas (GHG) emission trading systems reduce the competitiveness of fossil fuel projects in the market and accelerate investment in low‐carbon energy sources such as wind and photovoltaic power generation units. This market mechanism allows large entities such as countries and companies that emit GHGs into the atmosphere to buy and sell these gases. This paper reviews the blockchain solutions developed for carbon markets. Studies related to the design of smart contracts in the platform of blockchain are investigated. Special cryptocurrencies that are used in the field of green energy transactions and carbon trading are introduced. In addition, the application of artificial intelligence and game theory in energy trading is stated. The study of different blockchain frameworks for carbon trading shows that the use of decentralized platforms in carbon trading can have a significant impact on the trend towards low‐carbon measures and achieving the goals of the Kyoto Treaty, increasing the value of green cryptocurrencies and the volume of transactions. These technologies offer a promising avenue for creating a more decentralized, efficient, and environmentally conscious energy ecosystem.

show abstract

Section: Carbon Tradingmentioning

confidence: 99%

Towards the net zero carbon future: A review of blockchain‐enabled peer‐to‐peer carbon trading

Parhamfar,

Sadeghkhani,

Adeli

2024

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…A flexible FL architecture for intelligent transportation systems (ITS) is introduced by Lin et al 36 The leverages blockchain sharding to provide decentralized vehicular data exchanges between intelligent vehicles. It is suggested to use a streamline-based shard transmission technique to guarantee communication effectiveness nearly without sacrificing FL accuracy.…”

Section: Related Workmentioning

confidence: 99%

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

Maheswari,

Krishnamurthy

2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Side‐channel analysis (SCA) is a type of cryptanalytic attack that uses unintended ‘side‐channel’ leakage through the real‐world execution of the cryptographic algorithm to crack a secret key of an embedded system. These side‐channel errors can be discovered through tracking the energy usage of the device performing the technique, electromagnetic radiations while the encryption process, execution time, cache hits/misses, and others. Nowadays, deep learning‐based detection techniques are considered as emerging techniques that have been proposed for attack detection. Deep learning architectures have the ability to learn autonomously and concentrate on difficult features, in contrast to machine learning models. In light of these factors, the work's motive is thought to be the proposal of a deep learning‐based attack detection method. Many methods are used to decrease these assaults, however, the majority of them are inefficient and time‐demanding. In order to address these challenges, this study employs a novel deep learning‐based methodology. Pre‐processing, feature extraction, and SCA classification are the three stages of the approach proposed in this work. First, pre‐processing is used to remove unnecessary information and improve the quality of the input using data cleaning and min‐max normalization. The previously processed data are then fed as input into the proposed hybrid deep learning architecture. A Deep Residual Capsule Auto‐Encoder (DR_CAE) model is introduced in the proposed study. The deep residual neural network‐50 (DRNN‐50) is utilized to extract relevant features in this case, while the side channel analysis is done by using capsule auto‐encoder (CAE). The parameters of the proposed model are adjusted using the modified white shark optimization (MWSO) technique to improve its performance. In the results section, the proposed model is compared to various existing models in terms of accuracy, precision, recall, F‐measures, time, and so on. The proposed framework has an accuracy of 98.802%, F‐measures of 98.801%, kappa coefficient of 97.6%, the precision value of 98.81%, and recall value of 98.80%.

show abstract

BDACD: Blockchain-based decentralized auditing supporting ciphertext deduplication

Xu,

Jin,

Qin

et al. 2024

Journal of Systems Architecture

View full text Add to dashboard Cite

DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning

Cited by 10 publications

References 37 publications

Towards the net zero carbon future: A review of blockchain‐enabled peer‐to‐peer carbon trading

Towards the net zero carbon future: A review of blockchain‐enabled peer‐to‐peer carbon trading

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

BDACD: Blockchain-based decentralized auditing supporting ciphertext deduplication

Contact Info

Product

Resources

About