The development of data-driven artificial intelligence technology has given birth to a variety of big data applications. Data has become an essential factor to improve these applications. Federated learning, a privacy-preserving machine learning method, is proposed to leverage data from different data owners. It is typically used in conjunction with cryptographic methods, in which data owners train the global model by sharing encrypted model updates. However, data encryption makes it difficult to identify the quality of these model updates. Malicious data owners may launch attacks such as data poisoning and free-riding. To defend against such attacks, it is necessary to find an approach to audit encrypted model updates. In this paper, we propose a blockchain-based audit approach for encrypted gradients. It uses a behavior chain to record the encrypted gradients from data owners, and an audit chain to evaluate the gradients’ quality. Specifically, we propose a privacy-preserving homomorphic noise mechanism in which the noise of each gradient sums to zero after aggregation, ensuring the availability of aggregated gradient. In addition, we design a joint audit algorithm that can locate malicious data owners without decrypting individual gradients. Through security analysis and experimental evaluation, we demonstrate that our approach can defend against malicious gradient attacks in federated learning.
Vehicles share information via Vehicular Ad-hoc Network (VANET) that is considered the foundation of the intelligent transportation system. Access control from functional encryption (FE) allows secure sharing over encrypted data with both utilization and privacy. However, low-powerful vehicles and the untrusted server incurs that FE-based access control mechanisms are less practical with client-side inefficiency and access unreliability. In this work, we put forth ORAC,anOptimized encryptedAccessControl system with partial privacy andReliability. ORAC is built on top of functional encryption that guarantees data partial privacy and data utilization in VANET, and separates the data access into the offline phase and the online phase, such that most of decryption computation could be done in the offline phase and vehicles could execute the real decryption efficiently. By embedding blockchain transactions into identity records and data storage, ORAC protects data accessed by vehicles from tampering and thereby manages data transfers with high reliability. It can be instantiated directly from pairing-based assumptions and features only the decryption complexity of two exponentiation and two multiplication operations. We give a formal security proof of the instantiation in the semantic security model. We also prototype our scheme by implementing ORAC over Ethereum with two types of smart contracts and the evaluation can demonstrate its efficiency optimization.
Hongze Liu, Jie Li, Shijing Yuan, Wenqi Cao · 5 authors
Hierarchical Federated Learning (HFL) is introduced as a promising technique that allows model owners to fully exploit computational resources and bandwidth resources to train the global model. However, due to the high training cost, a single model owner may not be able to deploy HFL. To address this issue, we develop a smart contract based trust crowdfunding mechanism for HFL, which enables multiple model owners to obtain a crowdfunding model with high social utility for multiple crowdfunding participants. To ensure the authenticity of the crowdfunding mechanism, we implemented the Vickey-Clark-Croves (VCG) mechanism to encourage all crowdfunding participants and clients to provide realistic bids and offers. At the same time, in order to ensure guaranteed trustworthiness of crowdfunding and automatic distribution of funds, we develop and implement a smart contract to record the crowdfunding process and training results in the blockchain. We prove that the proposed scheme satisfies the budget balance and participant constraint. Finally, we implement a prototype of this smart contract on an Ethereoum private chain and evaluate the proposed VCG mechanism. The experimental results demonstrate that the proposed scheme can effectively improve social utility while ensuring the authenticity and trustworthiness of the crowdfunding process.
The healthcare profile of an individual is scattered across multiple data sources which can be difficult to access in a timely fashion. Furthermore, while the need to secure an individual’s personal health record is of paramount importance to prevent compromises such as cyber-attacks, it is important to be able to be able to seamlessly and quickly share information across healthcare providers to further enable precision and personalized health care. We present IntelliMedChain, a blockchain-powered knowledge-driven data sharing framework that gives patients complete control of their medical data and which can extract rich information hidden in the medical records using knowledge graphs (KGs). By incorporating both blockchain and KGs, we can provide a platform for a secure data sharing amongst stakeholders by maintaining data privacy and integrity through data authentication and robust data integration. We conduct a pilot study of the IntelliMedChain network using Ethereum blockchain technology to share knowledge across stakeholders. We show how it mitigates the issues around scalability by efficiently managing large-scale data and interoperability through seamless adoption of data regulations, as prescribed by various regulatory bodies for efficient governance.
Nguyen Quang Hieu, The Anh Tran, Cong Luong Nguyen, Dusit Niyato · 6 authors
Blockchain-enabled Federated Learning (BFL) enables model updates to be stored in blockchain in a reliable manner. However, one problem is the increase of the training latency due to the mining process. Moreover, mobile devices have energy and CPU constraints. Therefore, the machine learning model owner (MLMO) needs to decide the data and energy that the mobile devices use for the training and determine the block generation rate to minimize the system latency and mining cost while achieving the target accuracy. Under the uncertainty of BFL, we propose to use deep reinforcement learning to find the optimal decisions for the MLMO.
Seyednima Khezr, Abdulsalam Yassine, Rachid Benlamri, M. Shamim Hossain
Industrial Internet of Things (IIoT) devices generate and collect massive amounts of industrial data. Monetizing the flood of data generated by the IIoT devices has enabled the creation of the IIoT data ecosystem, where individuals and businesses may trade data. With the rapid expansion of the online data trading industry, the necessity for an edge intelligent reputation system is becoming increasingly important as more individuals and services connect online. In recent years, researchers have proposed blockchain-based reputation systems as a means of offering anonymity, security, transparency, and mutual trust for both providers and customers in Industry 4.0. Unfortunately, they focus on the decentralized reputation system with a single certificate authority, which creates the concern of a single point of failure (SPOF). Moreover, researchers paid little attention to the performance measures of these blockchain-based reputation systems to demonstrate their usability in a real IIoT data ecosystem. This article proposes a robust edge intelligent blockchain-based reputation system capable of avoiding failures by enhancing the Raft consensus mechanism. We provide extensive security analysis and simulation experiments to demonstrate the performance of the blockchain-based reputation system for the IIoT data ecosystem using different metrics, such as transaction throughput, latency, and resource consumption.
Spatial crowdsourcing emerges as a new computing paradigm that enables mobile users to accomplish spatio- temporal tasks in order to solve human-intrinsic problems. Existing crowdsourcing systems critically use centralized servers for interacting with workers and making task assignment decisions. These systems are hence susceptible to issues such as the single point of failure and the lack of operational transparency. Prior work, therefore, turns to blockchain-based decentralized crowdsourcing systems, yet still suffers from problems of lacking efficient task assignment scheme, requiring a deposit to an untrusted system, low block generation speed, and high transaction fees. To address these issues, we design a blockchain-based decentralized framework for spatial crowdsourcing, which we call SC-EOS. Our system does not rely on any trusted servers, while providing efficient and user-customizable task assignment, low monetary cost, and fast block generation. More importantly, it frees users from making a deposit into an untrusted system. Our framework can also be extended and applied to generic crowdsourcing systems. We implemented the proposed system on the EOS blockchain. Trace-driven evaluations involving real users show that our system attains the comparable task assignment performance against a clairvoyant scheme. It also achieves 10× cost savings than an Ethereum-based implementation.
Aiming at solving the security problems of data confidentiality and integrity in the traditional centralized Internet of things communication, data leakage and tampering caused by malicious users abusing communication functions in the Internet of things system, a data communication mechanism of Internet of things based on blockchain is proposed. Combined with the characteristics of blockchain, such as decentralization, immutability and auditability, the data exchange mechanism of Internet of things communication tunnel is proposed. Preventing malicious communication through communication tunnel management and control of data exchange between devices, and ensures data integrity in combination with digital signature technology. The security analysis shows that the mechanism has good security characteristics and meets the security requirements of Internet of things communication. Experiments on Ethereum show that compared with existing studies, this mechanism has less time overhead, indicating the feasibility and availability of this mechanism.
Many systems have recently begun to examine blockchain qualities in order to create cooperation enforcement methods. This paper provides a complete and extensive evaluation of work on multi-hop MANETs with blockchain-based trust control between nodes. We contextualize the snag of security in MANETs resulting from the lack of trust between the participating nodes. We present the blockchain concepts and discuss the limitation of the current blockchain in MANETs. We review the promising proposed ideas in the state-of-the-art based on research papers. Finally, we discuss and summarize strategies and challenges for further research.
Lianshan Sun, Xue Bai, Chao Zhang, Yang Li · 6 authors
In the Big Data era, data provenance has become an important concern for enhancing the trustworthiness of key data that are rapidly generated and shared across organizations. Prevailing solutions employ authoritative centers to efficiently manage and share massive data. They are not suitable for secure and trustworthy decentralized data provenance sharing due to the inevitable dishonesty or failure of trusted centers. With the advent of the blockchain technology, embedding data provenance in immutable blocks is believed to be a promising solution. However, a provenance file, usually a directed acyclic graph, cannot be embedded in blocks as a whole because its size may exceed the limit of a block, and may include various sensitive information that can be legally accessed by different users. To this end, this paper proposed the BSTProv, a blockchain-based system for secure and trustworthy decentralized data provenance sharing. It enables secure and trustworthy provenance sharing by partitioning a large provenance graph into multiple small subgraphs and embedding the encrypted subgraphs instead of raw subgraphs or their hash values into immutable blocks of a consortium blockchain; it enables decentralized and flexible authorization by allowing each peer to define appropriate permissions for selectively sharing some sets of subgraphs to specific requesters; and it enables efficient cross-domain provenance composition and tracing by maintaining a high-level dependency structure among provenance graphs from different domains in smart contracts, and by locally storing, decrypting, and composing subgraphs obtained from the blockchain. Finally, a prototype is implemented on top of an Ethereum-based consortium blockchain and experiment results show the advantages of our approach.
Mikael Beyene, Philipp A Toussaint, Scott Thiebes, Matthias Schlesner · 6 authors
OBJECTIVE: Rising interests in distributed ledger technology (DLT) and genomics have sparked various interdisciplinary research streams with a proliferating number of scattered publications investigating the application of DLT in genomics. This review aims to uncover the current state of research on DLT in genomics, in terms of focal research themes and directions for future research. MATERIALS AND METHODS: We conducted a scoping review and thematic analysis. To identify the 60 relevant papers, we queried Scopus, Web of Science, PubMed, ACM Digital Library, IEEE Xplore, arXiv, and BiorXiv. RESULTS: Our analysis resulted in 7 focal themes on DLT in genomics discussed in literature, namely: (1) Data economy and sharing; (2) Data management; (3) Data protection; (4) Data storage; (5) Decentralized data analysis; (6) Proof of useful work; and (7) Ethical, legal, and social implications. DISCUSSION: Based on the identified themes, we present 7 future research directions: (1) Investigate opportunities for the application of DLT concepts other than Blockchain; (2) Explore people's attitudes and behaviors regarding the commodification of genetic data through DLT-based genetic data markets; (3) Examine opportunities for joint consent management via DLT; (4) Investigate and evaluate data storage models appropriate for DLT; (5) Research the regulation-compliant use of DLT in healthcare information systems; (6) Investigate alternative consensus mechanisms based on Proof of Useful Work; and (7) Explore DLT-enabled approaches for the protection of genetic data ensuring user privacy. CONCLUSION: While research on DLT in genomics is currently growing, there are many unresolved problems. This literature review outlines extant research and provides future directions for researchers and practitioners.
Artificial intelligence (AI) and blockchain are two of the most disruptive technologies in recent years. Blockchain is widely regarded as a trust machine because of its decentralization, non-tampering, anonymity and traceability. AI provides machines with cognitive functions, including learning, reasoning, and adaptation based on the collected data, which enables human-like machines possess intelligence and decision-making capabilities. Also, both technologies are data-driven, and thus there are rapidly growing interests in integrating them for trustworthy artificial intelligence and intelligent blockchain. In this paper, we review the related research on the integration of AI and blockchain, mainly analyzing how blockchain technology can improve AI from five aspects and pointing out the future research direction of these two technologies. And our research shows that blockchain can drive various components of AI including data, algorithms, and computational power to higher levels.
Blockchains currently exist in silos, competing when they could be cooperating. Interoperability is essential to allow for communication between them and motivate mass adoption. In permissioned blockchains, interoperability is harder given their opaqueness. The solutions proposed so far to address interoperability require a trusted private third party, which may be insecure and is not ideal. We propose T-ODAP, a secure multi-layered protocol that enables a trustless solution for permissioned blockchain interoperability, eliminating the need for trust in the protocol’s participants. It provides a Decentralized View Storage, a connector that connects permissioned blockchains to the latter, and a trustless version of the ODAP protocol. T-ODAP models the participants as rational agents using game theory techniques and is implemented using \textit{Polkadot} and \textit{Hyperledger Cactus}. We tested the implemented solution, evaluated the system’s robustness in face of attacks, and concluded that the system is \textit{(k,t)-weak-robust}.
Rodrigo Dutra Garcia, Gowri Ramachandran, Raja Jurdak, Jó Ueyama
Real-world applications in healthcare and supply chain domains produce, exchange, and share data in a multi-stakeholder environment. Data owners want to control their data and privacy in such settings. On the other hand, data consumers demand methods to understand when, how, and who produced the data. These requirements necessitate data governance frameworks that guarantee data provenance, privacy protection, and consent management. We introduce a decentralized data governance framework based on blockchain technology and proxy re-encryption to let data owners control and track their data through privacy-enhancing and consent management mechanisms. Besides, our framework allows the data consumers to understand data lineage through a blockchain-based provenance mechanism. We have used Digital e-prescription as the use case since it has multiple stakeholders and sensitive data while enabling the medical fraternity to manage patients’ prescription data, involving patients as data owners, doctors, and pharmacists as data consumers. Our proof-of-concept implementation and evaluation results based on CosmWasm and pyUmbral PRE show that the proposed decentralized system guarantees transparency, privacy, and trust with minimal overhead.
Christian Killer, Moritz Eck, Bruno Rodrigues, Jan von der Assen · 6 authors
Recent years saw an increase in voting systems using public permissionless blockchains. Although public blockchains offer transparency and immutability, permissioned consensus is better suited for voting systems’ requirements, because an initial level of trust in authorities is always required. Hence, a permissioned Distributed Ledger (DL) immutably storing the voting system’s audit trail satisfies demands measurably.ProvotuMN 3.0 is a decentralized and receipt-Free (RF) voting system based on an end-to-end verifiable Re-Encryption Mixnet (RMN). RMNs allow for flexible votes and elections and decouple the ballot structure from the cryptographic voting protocol. Thus, ProvotuMN decentralizes trust (i) through the use of cryptographic shuffles and Non-Interactive Zero-Knowledge Proofs (NIZKP) in an RMN executed among DL nodes, (ii) by employing a distributed key generation for election keys, and (iii) by offering a decentralized re-encryption service assuring RF. Performance evaluations performed indicate that the voting scheme is scalable for large-scale voting.
Model migration can accelerate model convergence during federated learning on the Internet of Things (IoT) devices and reduce training costs by transferring feature extractors from fast to slow devices, which, in turn, enables sustainable computing. However, malicious or lazy devices may migrate the fake models or resist sharing models for their benefit, reducing the desired efficiency and reliability of a federated learning system. To this end, this work presents a blockchain-based model migration approach for resource-constrained IoT systems. The proposed approach aims to achieve secure model migration and speed up model training while minimizing computation cost. We first develop an incentive mechanism considering the economic benefits of fast devices, which breaks the Nash equilibrium established by lazy devices and encourages capable devices to train and share models. Second, we design a clustering-based algorithm for identifying malicious devices and preventing them from defrauding incentives. Third, we use blockchain to ensure trustworthiness in model migration and incentive processes. Blockchain records the interaction between the central server and IoT devices and runs the incentive algorithm without exposing the devices’ private data. Theoretical analysis and experimental results show that the proposed approach can accelerate federated learning rates, reduce model training computation costs to increase sustainability, and resist malicious attacks.
Truc Nguyen, Phuc Thai, Tre’ R. Jeter, Thang N. Dinh · 5 authors
Despite the great potential of Federated Learning (FL) in large-scale distributed learning, the current system is still subject to several privacy issues due to the fact that local models trained by clients are exposed to the central server. Consequently, secure aggregation protocols for FL have been developed to conceal the local models from the server. However, we show that, by manipulating the client selection process, the server can circumvent the secure aggregation to learn the local models of a victim client, indicating that secure aggregation alone is inadequate for privacy protection. To tackle this issue, we leverage blockchain technology to propose a verifiable client selection protocol. Owing to the immutability and transparency of blockchain, our proposed protocol enforces a random selection of clients, making the server unable to control the selection process at its discretion. We present security proofs showing that our protocol is secure against this attack. Additionally, we conduct several experiments on an Ethereum-like blockchain to demonstrate the feasibility and practicality of our solution.
Due to the transparency of blockchain, adversaries can observe the details of a transaction, and then utilize the amount as a unique quasi-identifier to make deanonymization. Nowadays, to obscure the linkages between receivers and senders within a transaction on the blockchain, mixing services are widely applied in many real applications to enhance cryptocurrencies' anonymity. The basic idea of mixing services is to hide an output within several other outputs in a transaction such that adversaries cannot distinguish them by their amounts since they are purposely selected to have the same amount. For a set of original outputs with different amounts, mixing services need to decompose them into a set of decomposed outputs, where any decomposed output has some other decomposed outputs with the same amount. Since the transaction fee is related to the number of outputs, we are motivated to decompose original outputs into a minimal set of decomposed outputs, which is challenging to guarantee the privacy-preserving effect at the same time. In this paper, we formally define the anonymity-aware output decomposition (AA-OD) problem, which aims to find a c-decomposition with a minimum number of decomposed outputs for a given original output set. A c-decomposition guarantees that for any original output$o$, there are at most$c$of all decomposed outputs with an amount of$x$coming from$o$. We prove that the AA-OD problem is NP-hard. Thus, we propose an approximation algorithm, namely Boggart11Boggart is a magical creature in J. K. Rowling's Harry Potter series who can shift his shape and no one knows what it looks like., to solve the AA-OD problem with a (2/c + 3)-approximation bound on the number of decomposed outputs. We verify the efficiency and effectiveness of our approach through comprehensive experiments on both real and synthetic data sets.
Permissioned blockchain is increasingly being used as a collaborative platform for sharing data. However, current blockchain-based data sharing is unable to balance privacy pro-tection and query functionality, limiting its application scenarios. Order-preserving encryption/encoding (OPE) allows encrypting data to prevent privacy leakage while still supporting efficient order-oriented queries on ciphertexts. But existing OPE schemes are constrained by limited use cases and inherent performance limitations that make them difficult to be adopted by permissioned blockchain where performance is a major concern. In this paper, we present BlockOPE, an efficient OPE scheme designed around the first study integrating OPE into blockchain systems. By supporting parallel processing with a conflict-reducing design, we argue that BlockOPE is feasible for permissioned blockchain, achieving orders-of-magnitude performance improvement while preserving the ideal OPE security. Additionally, we improve query processing by leveraging an adaptive lightweight client cache. Extensive experiment results and theoretical analysis illustrate the practicability of our approach.
Zero-knowledge blocklists allow cross-platform blocking of users but, counter-intuitively, do not link users identities inter- or intra-platform, or to the fact they were blocked. Unfortunately, existing approaches (Tsang et al. ’10) require that servers do work linear in the size of the blocklist for each verification of a non-membership proof.We design and implement SNARKBLOCK, a new protocol for zero-knowledge blocklisting with server-side verification that is logarithmic in the size of the blocklist. SNARKBLOCK is also the first approach to support ad-hoc, federated blocklisting: websites can mix and match their own blocklists from other blocklists and dynamically choose which identity providers they trust.Our core technical advance, of separate interest, is the HICIAP zero-knowledge proof system, which addresses a common problem in privacy-preserving protocols: using zero-knowledge proofs for repeated but unlinakble interactions. Rerandomzing a Groth16 proof achieves unlinkability without the need to recompute the proof for every interaction. But this technique does not apply to applications where each interaction includes multiple Groth16 proofs over a common hidden input (e.g., the user’s identity). Here, the best known approach is to commit to the hidden input and feed it to each proof, but this creates a persistent identifier, forcing recomputation. HICIAP resolves this problem by aggregating n Groth16 proofs into one $O(\log n) -$sized, $O(\log n) -$verification time proof which also shows that the input proofs share a hidden input. Because HICIAP is zero-knowledge, repeated shows of the same aggregate or an updated aggregate are unlinkable even though the underlying Groth16 proofs are never recomputed.
Centralization has dominated classic scientific, social, and economic developments. Decentralization has also received increasing attention in management, decision, governance, and economics, despite its incomparability in AI. Going beyond centralized and distributed AI, this article reviews and delineates the conceptual map, research issues, and technical opportunities of decentralized AI and edge intelligence. The complementarity and metasynthesis between centralized and decentralized AI are also elaborated. We further assess where decentralized AI and edge intelligence can enable and promote smart blockchain, Web3, metaverse and decentralized science disciplinarily, technically, practically, and more broadly.
Samuel Steffen, Benjamin Bichsel, Roger Baumgartner, Martin Vechev
Data privacy is a key concern for smart contracts handling sensitive data. The existing work zkay addresses this concern by allowing developers without cryptographic expertise to enforce data privacy. However, while zkay avoids fundamental limitations of other private smart contract systems, it cannot express key applications that involve operations on foreign data.We present ZeeStar, a language and compiler allowing non-experts to instantiate private smart contracts and supporting operations on foreign data. The ZeeStar language allows developers to ergonomically specify privacy constraints using zkay’s privacy annotations. The ZeeStar compiler then provably realizes these constraints by combining non-interactive zero-knowledge proofs and additively homomorphic encryption.We implemented ZeeStar for the public blockchain Ethereum. We demonstrated its expressiveness by encoding 12 example contracts, including oblivious transfer and a private payment system like Zether. ZeeStar is practical: it prepares transactions for our contracts in at most 54.7s, at an average cost of 339k gas.