Jul 2026· Annual International Computer Software and Applications Conference· pp. 962-967· 0 citations· 25 references
Abstract
Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping data decentralized. However, traditional FL architectures suffer from critical trust issues, including vulnerability to model poisoning attacks, a lack of incentives for honest participation, and the inability to verify the quality of submitted model updates. Blockchain-based solutions have been proposed to address these challenges, but they often require participants to bootstrap independent validator networks and lock additional capital, limiting scalability and practical adoption. This paper proposes EigenFL, a novel FL framework secured through blockchain restaking, leveraging EigenLayer to provide cryptoeconomic security and decentralized validation by reusing Ethereum's existing validator infrastructure. Participants are economically incentivized to submit honest updates, while malicious behavior is discouraged through slashing mechanisms. Model updates are validated off-chain by independent operators, and their outcomes are immutably recorded on-chain, ensuring accountability and robustness. EigenFL demonstrates how blockchain restaking can transform FL from a trust-based paradigm into a cryptoeconomically secured framework, enabling verifiable and decentralized training.
Federated learning helps in collaborative training of AI models without transmitting raw data, and hence it is an exciting approach for privacy-conscious applications. Nonetheless, traditional federated learning still suffers from weaknesses such as susceptibility to attacks from malicious actors, susceptibility to model poisoning, single point of coordination, lack of transparency, and scalability issues. Blockchain technology provides a decentralized method of trusting which can help in enhancing the security, accountability, and integrity of federated learning. This paper presents a comprehensive analysis of blockchain based trustworthy federated learning through the examination of the role played by consensus algorithms, cryptographic security techniques, scalability approaches, and deployment strategies. A systematic literature review was conducted using recently published papers from peer-reviewed sources. The selected papers were analyzed using inclusion and exclusion criteria to reveal technological advancements, deployment problems, and practical applications. Consensus methods, which include Proof of Stake, Practical Byzantine Fault Tolerance, Delegated Proof of Stake, and hybrid versions, illustrate various tradeoffs between security, processing speed, latency, and energy utilization. Encryption algorithms like homomorphic encryption, secure multiparty computation, differential privacy, and digital signatures offer added value to privacy and resilience against malicious activity. The review presents several shortcomings concerning communication overheads, blockchain storage expansion, delays in the consensus process, interoperability, and resource-limited edge computing nodes. Recent innovations, such as lightweight consensus, hierarchical blockchain structures, off-chain storage, and adaptive communication models, reveal high prospects in addressing those shortcomings. This research reveals that federated learning by blockchain is a robust and scalable platform to enable privacy-preserving artificial intelligence in healthcare, finance, IoT, smart city, and industrial applications.
Arthi D, R Anand, Palaniappan Sambandam et al.· International journal of com...· 0 citations
Federated Learning (FL) allows multiple data possessors to collaboratively train a shared model without transferring any raw data outside their local administration limits. However, conventional server orchestrated FL is vulnerable to trusted-server reliance, black-box contribution auditability, malicious model updates, and weak accountability. This article proposes a trust-based federated learning framework in which a smart contract enabled by blockchain oversees client registration, model update logging, hash-based integrity verification, trust score calculation, malicious node penalization, aggregation approval, and decentralised audit logging.
The paper uses a clearly labelled simulated experimental setup involving 16 clients having a non-IID Fashion-MNIST classification task. Three of these 16 clients are malicious and submit either poisoned updates or updates having hash mismatches. The proposed trust-centric blockchain federated learning configuration is compared with traditional federated averaging based on parameters such as model accuracy, verification rate, malicious-update identification, F1-score, transaction cost, and governance traceability. Based on the simulation results, the new framework enhances the global accuracy from 79.6% to 86.8% under the attack setting. Further hash-verification coverage is complete for submitted updates. Likewise, the simulation rejects the three malicious submissions in the simulated round. Lastly, the provenance records become immutable via incurring additional latency of 121.3 ms per update. The paper contributes a technically defined, IEEE-style framework for federated learning, smart-contract trust scoring, model-integrity verification, and decentralized AI governance. The outcomes are not offered as evidence of real-world deployment but as a reproducible academic design and evaluation framework for future empirical real-world deployment.
Shankar Thalla· International Journal of Lat...· 0 citations
Federated Learning (FL) enables distributed machine learning without sharing raw data, but its reliance on a central aggregation server introduces critical vulnerabilities gradient inversion attacks, Byzantine poisoning, free-riding by rational participants, and single-point-of-failure risk. Blockchain has been proposed as a structural remedy, giving rise to the field of Blockchain-Enabled Federated Learning (BEFL). reviews exactly eight representative peer-reviewed BEFL systems published selected to cover four core challenge dimensions: privacy, security, scalability, and incentive design. compare each system across accuracy under data heterogeneity, formal privacy guarantees, Byzantine robustness, throughput, and communication efficiency. find that every reviewed system excels on one or two dimensions while underperforming on others, and that no single published system simultaneously resolves all four challenges. Based on this review identify four fundamental research gaps and conclude with a structured research agenda. This study also reveals that the base FL optimizer contributes more to model accuracy than any blockchain or privacy mechanism a finding with significant design implications.
Raman Dubey, A. Jain, Richa Sharma· International Conference on...· 0 citations
Federated learning (FL) enables distributed clients to collaboratively train machine learning models without sharing raw data, making it well-suited for edge computing environments. However, deploying FL at the edge introduces critical challenges, including potential model poisoning by malicious clients or edge servers, increased privacy risks, and communication bottlenecks. To address these issues, we propose a two-layer blockchain-assisted FL framework that ensures privacy, robustness, and efficiency. In our design, each client uploads an encrypted local update to an edge server for privacy-preserving validation, while a lightweight, sparse upload strategy is adopted to reduce communication overhead. We design a two-layer defense strategy that employs the secure cosine similarity technique and a truth discovery algorithm to resist Byzantine attacks from both malicious clients and edge servers, while a consortium blockchain maintained by edge servers guarantees decentralized and tamper-resistant global model updates. Theoretical analysis and extensive experiments under both IID and non-IID data partitions demonstrate that the proposed scheme effectively defends against targeted and untargeted poisoning attacks and preserves the privacy of local model updates. It also substantially reduces communication overhead. These results indicate that our framework provides a practical and scalable solution for privacy-preserving and robust FL in edge environments.
Xiaodong Shen, Chang Xu, Liehuang Zhu et al.· IEEE Internet of Things Jour...· 0 citations
Collaborative threat intelligence sharing has become essential for defending distributed enterprise and smart city infrastructures against increasingly sophisticated cyber threats. However, organizations remain reluctant to share raw security data due to privacy, regulatory, and trust concerns. Federated Learning (FL) has emerged as a promising solution by enabling collaborative model training without exposing local data. Nevertheless, traditional FL-based intrusion detection frameworks remain vulnerable to model poisoning, Byzantine attacks, and lack transparent accountability mechanisms for cross-organization collaboration. This paper proposes an engineering framework for privacy-preserving federated threat intelligence sharing that integrates trust-aware robust aggregation with blockchain-based integrity anchoring. The proposed architecture introduces a dynamic reputation mechanism that evaluates participant reliability across communication rounds and assigns adaptive aggregation weights to mitigate malicious updates. To enhance transparency and non-repudiation, model update hashes and trust evolution records are anchored on a permissioned blockchain through smart contracts, ensuring immutable auditability without exposing sensitive parameters. The framework is evaluated using a non-IID partition of the ToN-IoT dataset across multiple simulated organizations. Experimental results demonstrate significant robustness improvements under adversarial environments. Under Byzantine attacks with 20% malicious clients, the proposed trust-aware aggregation mechanism achieves approximately 95% Accuracy and 95% F1-macro, compared with approximately 89% obtained using conventional FedAvg. Furthermore, under highly adversarial conditions involving 40% malicious participants, the proposed framework maintains approximately 95% Accuracy and F1-macro, whereas FedAvg degrades to approximately 78% Accuracy and 77% F1-macro. These results confirm the effectiveness of the proposed trust-aware aggregation mechanism in mitigating malicious updates while preserving stable convergence and reliable intrusion detection performance.
Mehdi Houichi, Faouzi Jaidi, Adel Bouhoula· Journal of King Saud Univers...· 0 citations
Federated Learning (FL) enables collaborative model training across decentralized participants without sharing raw data. However, existing FL systems remain vulnerable to Byzantine attacks and suffer from a lack of accountability, verifiability, and economic incentives for honest participation. We present BFL-Guard, a novel blockchain-orchestrated federated learning framework integrating: (i) zk-SNARK-based zero-knowledge gradient proofs, (ii) an on-chain Byzantine-tolerant aggregation smart contract, and (iii) a tokenized incentive protocol (FedToken). BFL-Guard stores model checkpoints as IPFS hashes anchored on Ethereum, ensuring tamper-evident auditability. Experiments on CIFAR-10 and Shakespeare benchmarks demonstrate 95.2% and 87.6% accuracy in IID and Non-IID settings, surpassing all baselines while converging 12.4% faster even under 30% Byzantine injection.
Kumaresan S, Thirumal L, Ellappan V et al.· International Journal of Lat...· 0 citations