With the exponential growth in the number of Internet-of-Things (IoT) devices, the cloud-centric computing paradigm can hardly meet the increasingly high requirements for low latency, high bandwidth, ease of availability, and more intelligent services. Therefore, a distributed and decentralized computing architecture is imperative, where edge-centric computing, such as fog computing and mist computing, has been recently proposed. Edge-centric computing resources can be managed locally and personally rather than being administered by a remote centralized third party. However, security and privacy issues are the main challenges due to the absence of trust between the IoT devices and edge computing nodes (ECNs). A blockchain, as a decentralized, trustless, and immutable public ledger, can well solve the trust-absence issue. In this article, we first elaborate on the security and privacy issues of edge-computing-enabled IoT, and then present the key characteristics of blockchains, which make blockchains well suited for the edge-centric IoT scenarios. Furthermore, we propose a general framework for blockchain-based edge-computing-enabled IoT scenarios that specifies the step-by-step procedure of a single transaction between an IoT end and an ECN. In addition, we design a smart contract within a private blockchain network that exploits the state-of-the-art machine learning algorithm, asynchronous advantage actor-critic (A3C), to allocate the edge computing resources, which exemplifies how artificial intelligence (AI) can be combined with blockchains. We further discuss the benefits of the convergence of AI and blockchains. Finally, simulation results are presented.
Jacques Bou Abdo, Rayane El Sibai, Jacques Demerjian
Abstract Over the past years, blockchain technology has become more and more interesting since its ability to carry out transactions without any mediator. To ensure the transactions' reliability, consensus algorithms are adopted by blockchain technology. However, due to the failure of consensus algorithms in managing nodes' identities, blockchain technology is considered inappropriate for many applications. In this article, we propose the permissionless proof‐of‐reputation‐X (PL‐PoRX) that upgrades an existing consensus algorithm, the proof‐of‐reputation‐X (PoRX). PL‐PoRX replaces the trusted identity database in PoRX with a new admission process to make the algorithm suitable for permissionless blockchains, while maintaining PoRX's reputation mechanism. Several experiments are conducted to show the efficiency of our approach under different scenarios. We also debate the security model of the new protocol and study its time complexity. The results show that PL‐PoRX decreases the number of blocks issued by malicious miners, and help benign miners build reputation faster.
Korkmaz Caner, Halil Eralp Kocas, Uysal Ahmet, Ahmed Masry · 6 authors
Federated learning is a collaborative machine learning mechanism that allows multiple parties to develop a model without sharing the training data. It is a promising mechanism since it empowers collaboration in fields such as medicine and banking where data sharing is not favorable due to legal, technical, ethical, or safety issues without significantly sacrificing accuracy. In centralized federated learning, there is a single central server, and hence it has a single point of failure. Unlike centralized federated learning, decentralized federated learning does not depend on a single central server for the updates. In this paper, we propose a decentralized federated learning approach named Chain FL that makes use of the blockchain to delegate the responsibility of storing the model to the nodes on the network instead of a centralized server. Chain FL produced promising results on the MNIST digit recognition task with a maximum 0.20% accuracy decrease, and on the CIFAR-10 image classification task with a maximum of 2.57% accuracy decrease as compared to non-FL counterparts.
Proof of Work (PoW) is the consensus protocol introduced with Bitcoin, and is still one of the most used protocols, thanks to its security properties. However, it is very expensive in terms of energy consumption. For this reason, many other protocols have been designed in order to earmark part of the computations for useful tasks, or to reduce them, but few of these have the same properties of PoW.With this paper we propose a new consensus protocol for blockchains, called Proof of Evolution (PoE), that keeps the security features of PoW, and uses part of the mining computations for the execution of genetic algorithms (GAs) that some clients can submit. Moreover, PoE enables a form of cooperation among miners. During the mining process, in fact, miners have to maintain and evolve a population of solution candidates; PoE offers them the possibility of sharing their current best found solutions, that they can add to their population. This exchange seems to enhance the quality of the solutions they can achieve with the GAs in use. PoE is close to Proof of Search (PoS), which in turn extends PoW in order to solve optimization problems while mining. While PoS stimulates miners in submitting solutions for a problem of interest, the contribution of PoE is to encourage them to share their current best found solutions, allowing cooperation.
Gustavo F. Camilo, Gabriel Antonio F. Rebello, Lucas Airam C. de Souza, Otto Carlos M. B. Duarte
Every citizen has the right to privacy and, therefore, the right to control their personal information, deciding to whom, when, and where their information is available. This paper proposes a secure, agile, and effective system for a distributed, automatic, and transparent data trading between domains using blockchain, smart contracts, trust, and reputation. We develop and implement a prototype of a trust and reputation system based on real-life interactions. The results show that the proposed system provides security and privacy in a quick and distributed way, performing hundreds of transactions per second, and effectively punishing malicious behavior.
We propose Agora, the first privacy-aware data marketplace that enables parties to get compensated for contributing data, without relying on a trusted third party. We leverage cryptographic techniques to achieve three security properties: (i) data privacy-raw data remain private except for a function output, (ii) output verifiability-the output is proven to be correct, and (iii) atomicity of payments-parties cannot avoid paying for provided services. Agora is designed as a decentralized blockchain application via smart contracts. We implement a prototype on Ethereum and evaluate its performance in terms of computation overhead and monetary cost.
Secure multiparty protocols are useful tools for parties wishing to jointly compute a function while keeping their input data secret. The millionaires' problem is the first secure two-party computation problem, where the goal is to securely compare two private numbers without a trusted third-party. There have been several solutions to the problem; however, these solutions are either insecure in the malicious model or cannot verify the validity of inputs. In this paper, we introduce Variance, a privacy-preserving two-party protocol for solving Yao's millionaires' problem in a Bitcoin setting, in which each party controls several Bitcoin accounts (single and multi signature addresses) and they want to find out who owns more bitcoins without revealing (1) how many accounts they own or the addresses associated with their accounts, (2) the balance of any of their accounts, and (3) their total wealth of bitcoins while assuring the other party that they are not claiming more bitcoin than they possess. We utilize zero knowledge proofs to provide a solution to the problem, and subsequently prove that Variance is secure against active adversaries in the malicious model.
Xiaobing Guo, Qingxiao Guo, Min Liu, Yunhao Wang · 6 authors
Blockchain is multi-centralized, immutable and traceable, thus is very suitable for distributed storage, privacy and security management in IoTs. However, most existing researches focus on the integration of public blockchain and IoTs. In fact, problems such as slow consensus, low transmission throughput, and completely open storage on the public blockchain are intolerable in IoT scenarios. Although consortium blockchain represented by Hyperledger Fabric has improved the transmission rate, its data security completely relies on the PKI-based certificate mechanism, resulting in transmission inefficiency and privacy leakage. In this paper, a key-derived Controllable Lightweight Secure Certificateless Signature (CLS2) algorithm is proposed to significantly improve the transmission efficiency and keep similar computation overhead of consortium blockchain. Compared with the existing certificateless signatures, CLS2achieves more secure transactions, whose controllable anonymity and key-derived mechanism not only prevents public key replacement attacks and forged signature attacks, but also supports hierarchical privacy protection. Armed with CLS2, we design a consortium blockchain security architecture based on Hyper-ledger Fabric and edge computing. To the best of our knowledge, this is the first implementation of certificateless signature in consortium blockchain. We formally prove the security of our schemes in the random oracle model. Specifically, the security of the proposed scheme is reduced to the Elliptic curve discrete logarithm problem (ECDLP). Security analysis and experiments in IoT scenarios verify the feasibility and effectiveness of CLS2.
Collaborative learning techniques allow numerous clients conjointly to improve artificial intelligence models using their private datasets. The clients carry out the training locally and periodically exchanging gradient values through devices. Unlike conventional training approaches, the training data in the collaborative techniques are not revealed publicly. Regardless of privacy merits, clients are often less motivated to improve the model due to inadequate incentives procedural. In short, the resources owned are not maximally utilized. To tackle the issue, we design a collaborative learning model with a secure, fair, and immutable incentive mechanism by leveraging blockchain technology. Incentives are distributed proportionately to clients according to their respective contributions. We implement our incentive schemes on Ethereum. We also evaluate the performance of collaborative learning in a different setting. The results indicate that the design objectives are met.
Blockchain is an especially promising and revolutionary technology that brings transparency in a scalable way for multiple organizations and this is thanks to its several features. There are some exciting blockchain features but among them, decentralization is undoubtedly the most interesting one. Organizations can share data within a distributed ledger. As a consequence, each one can access synchronized data stored in its local Blockchain node. This functionality improves transaction tracking and facilitates access to data within a private group of organizations. However, in some cases, even if organizations accept to share data, they require to hide some private information related to their users or their business model. To tackle privacy and trust issues between organizations, this paper presents a blockchain architecture based on the proxy re-encryption scheme. This scheme is integrated within smart contracts to provide a very efficient, fast, and secure platform. The proposed architecture is implemented in an Hyperledger Blockchain and tested in a real transport and mobility use case.
Beyond fifth generation (B5G) networks have recently emerged as the advancement of existing communication systems. With the unprecedented proliferation of artificial intelligence (Ai), more intelligent B5G networks are projected to fuel the continuous development of Ai applications and the efficiency of communication technologies. More recently, the outgrowths of B5G have brought billions of devices throwing zillions of bytes of data to network edges. Training such huge data volumes using a centralized data center proves to be a challenging task, due to prohibitively heavy bandwidth costs, poor time efficiency, and high privacy leakages. These challenges have fueled the revolutionary shift of intelligence applications from a centralized data center to ubiquitous edges, denoted as edge intelligence. However, there is still a long way ahead before edge intelligence is able to fully mature. Governing and sharing the use of learning results efficiently, reliably, and safely are hampered by the heterogeneity and non-confidence among edges. in this article, we propose blockchain energized edge intelligence for B5G networks, called the Ai-Chain, fusing deep learning and blockchain. The Ai-Chain is a distributed and immutable record of learning results that is able to construct a new basis of sharing among edges. Additionally, we consider a novel learning-based consensus protocol in the Ai-Chain, denoted as proof of learning (PoL). in response to the huge computing power waste, PoL treats the training process as a working puzzle, rather than the meaningless hashing in a proof of work protocol. On the other hand, PoL fully unlocks the potential of sharing more advanced intelligence among edges. in order to demonstrate the effectiveness of the Ai-Chain, we employ it to solve a joint resource allocation problem in B5G networks. Experimental results prove the superior performance of the Ai-Chain to the current popular scheme.
Jonathan Passerat‐Palmbach, Tyler Farnan, Mike McCoy, Justin D. Harris · 7 authors
Machine learning and blockchain technology have been explored for potential applications in medicine with only modest success to date. Focus has shifted to exploring the intersection of these technologies along with other privacy preserving encryption techniques for better utility. This combination applied to federated learning, which allows remote execution of function and analysis without the need to move highly regulated personal health information, seems to be the key to successful applications of these technologies to rapidly advance evidence-based medicine. We give a brief history of these technologies in medicine, outlining some of the challenges with successful use. We then explore a more detailed combination of usage with an emphasis on decentralizing or federating the learning process along with auditability and incentivization blockchain can allow in the machine learning process. Based on the cost-benefit analysis of previous efforts, we provide the framework for an advanced blockchain-orchestrated machine learning system for privacy preserving federated learning in medicine and a new utility in health. Six critical elements for this approach in the future will be:(a) Data and analytic processes discoverable on secure public blockchain while retaining privacy of the data and analytic processes(b) Value fabricated by generating data/compute matches that were previously illegal, unethical and infeasible(c) Compute guarantees provided by federated learning and advanced cryptography(d) Privacy guarantees provided by software (e.g., Homomorphic Encryption, Secure Multi-Party Computation, ...) and hardware (e.g., Intel SGX and AMD SEV-SNP) cryptography(e) Data quality incentivized via tokenized reputation-based rewards(f) Discarding of poor data accomplished via model poisoning attack prevention techniques.
Privacy-Preserving Technologies in Data
Blockchain Technology Applications and Security
Artificial Intelligence in Healthcare and Education
Nida Khan, Abdelkader Lahmadi, Zsófia Kräussl, Radu State
Blockchain has emerged as a novel solution addressing a plethora of industrial issues in domains spanning from financial to educational. However, several challenges restrict the widespread adoption of the technology and data privacy, with throughput and scalability issues, ranks amongst the foremost. In this paper, we introduce a novel privacy management plane which integrates differential privacy to query existing relational databases through the blockchain as well as spearheads the use of blockchain for local differential privacy. The distinguishing feature in the latter is that the privacy management plane gives the data owners the right to perturb their data with the desired privacy budget, while in the former it gives the right to the data curator to change the privacy budget dynamically while answering queries through the blockchain. The paper also includes experimental evaluation of the developed privacy management plane and integrates management operations in it through another smart contract. The paper addresses the issue of GDPR and it's implications in the context of blockchain data, while highlighting the compliance of the proposed implementation.
Liming Fang, Bo Zhao, Li Yang, Zhe Liu · 6 authors
The development of 5G has substantially increased the destructiveness of DoS/DDoS attacks because the data processing capability of computers has not been accordingly enhanced, and this contradiction creates a vulnerability for attackers to compromise a server by sending a massive data flow. in practical 5G circumstances, it is difficult to extract distinct features between malicious and benign massive data flows. This amplifies the difficulties of DoS/DDoS detection. Thus, precautions against DoS/DDoS attack in 5G are of great importance. in this article, we present a solution based on smart contracts and machine learning as a countermeasure against DoS/DDoS attacks in the 5G background by hiding a protected server in a blockchain network and flexibly restricting the scale of DoS/DDoS via transaction fees. We also leverage non-repudiation of smart contracts, analyzing users' malicious behavior of communication and executing punishment via smart contracts. Our scheme could effectively mitigate massive DoS/DDoS attacks in advance and dynamically punitively charge DoS/DDoS attacks. Compared to existing DoS/DDoS defense in 4G, our scheme offers numerous benefits, including making benign communication always dominate rational users and countering DoS/DDoS attacks before they are launched. Moreover, compared to common DoS/DDoS detection based on Ai, we consider the source trustworthiness of training samples and take measures to avoid backdoors where model trainers may compromise Ai models to launch DoS/DDoS attacks.
Dara Tith, Joong-Sun Lee, H. Suzuki, W. M. A. B. Wijesundara · 7 authors
OBJECTIVES: Currently, patients' consent is essential to use their medical records for various purposes; however, most people give their consent using paper forms and have no control over it. Healthcare organizations also have difficulties in dealing with patient consent. The objective of this research is to develop a system for patients to manage their consent flexibly and for healthcare organizations to obtain patient consent efficiently for a variety of purposes. METHODS: We introduce a new e-consent model, which uses a purpose-based access control scheme; it is implemented by a blockchain system using Hyperledger Fabric. All metadata of patient records, consents, and data access are written immutably on the blockchain and shared among participant organizations. We also created a blockchain chaincode that performs business logic managing patient consent. RESULTS: We developed a prototype and checked business logics with the chaincode by validating doctors' data access with purpose-based consent of patients stored in the blockchain. The results demonstrate that our system provides a fine-grained way of handling medical staff 's access requests with diverse intended purposes for accessing data. In addition, patients can create, update, and withdraw their consents in the blockchain. CONCLUSIONS: Our consent model is a solution for consent management both for patients and healthcare organizations. Our system, as a blockchain-based solution that provides high reliability and availability with transparency and traceability, is expected to be used not only for patient data sharing in hospitals, but also for data donation for biobank research purposes.
This paper we propose a distributed computing architecture, the federated Learning based on the consortium blockchain. With decentralized distributed training, the federated learning modeling process is more robust, it can solve the current fairness and security problems of federated learning. We research the modeling efficiency problems in the Consortium Blockchain Federated Learning (CBFL) architecture at model training process, using model compression to improve the modeling efficiency, and we analyze Practical Byzantine Fault Tolerance consensus algorithm commonly used in the consortium chain, and propose the improvement of PBFT algorithm on the consensus efficiency and mechanism fault tolerance. The experiment results show that the improved CBFL has better practicability.
The problem of fair exchange consists of interchanging goods between two parties that do not trust each other. Despite known impossibility results, recent works leverage the block-chain and zero-knowledge proofs to implement zero-knowledge contingent payment (zkCP) systems that make fair exchange of digital goods possible. Implementing these systems in a secure and efficient way is a big challenge, as evidenced by several unsuccessful attempts from the literature. Campanelli et al. (ACM CCS 2017) discovered a vulnerability on an existing zkCP proposal based on SNARKs (succinct non-interactive arguments of knowledge) and suggested several repairs. Fuchsbauer (ACM CCS 2019) found a flaw in the mentioned countermeasures. In particular, he showed that witness-indistinguishability (WI) is not sufficient for the zkCP schemes proposed by Campanelli et al. to be secure. In this work, we observe that a slightly stronger notion of WI, that we coin trapdoor subversion WI (tS-WI), rules out Fuchsbauer's attack. We formally define security properties for CP systems and show that, under tS-WI, Campanelli et al.'s proposal indeed satisfies these properties. Additionally, we explore alternative approaches to implement ZK (other than SNARKs) and develop a prototype, using it to demonstrate their potential. Our new ideas result in a protocol to sell ECDSA signatures with contingent payment that can be executed in less than $150$ milliseconds over a LAN network.
Jiaheng Zhang, Zhiyong Fang, Yupeng Zhang, Dawn Song
Machine learning has become increasingly prominent and is widely used in various applications in practice. Despite its great success, the integrity of machine learning predictions and accuracy is a rising concern. The reproducibility of machine learning models that are claimed to achieve high accuracy remains challenging, and the correctness and consistency of machine learning predictions in real products lack any security guarantees. In this paper, we initiate the study of zero knowledge machine learning and propose protocols for zero knowledge decision tree predictions and accuracy tests. The protocols allow the owner of a decision tree model to convince others that the model computes a prediction on a data sample, or achieves a certain accuracy on a public dataset, without leaking any information about the model itself. We develop approaches to efficiently turn decision tree predictions and accuracy into statements of zero knowledge proofs. We implement our protocols and demonstrate their efficiency in practice. For a decision tree model with 23 levels and 1,029 nodes, it only takes 250 seconds to generate a zero knowledge proof proving that the model achieves high accuracy on a dataset of 5,000 samples and 54 attributes, and the proof size is around 287 kilobytes.
5G communications proposed significant improvements over 4G in terms of efficiency and security. Among these novelties, the 5G Network Slicing seems to have a prominent role: deploy multiple virtual network slices, each providing a different service with different needs and features. Like this, a Slice Operator (SO) ruling a specific slice may want to offer a service for users meeting some requirements. It is of paramount importance to provide a robust authentication protocol, able to ensure that users meet the requirements, but providing at the same time a privacy-by-design architecture. This makes even more sense having a growing density of Internet of Things (IoT) devices exchanging private information over the network. In this paper, we improve the 5G network slicing authentication using a Self-Sovereign Identity (SSI) scheme: granting users full control over their data. We introduce an approach to allow a user to prove his right to access a specific service without leaking any information about him. Such an approach is SANS, a protocol that provides non-linkable protection for any issued information, preventing an SO or an eavesdropper from tracking users' activity and relating it with their real identities. Furthermore, our protocol is scalable and can be taken as a framework for improving related technologies in similar scenarios, like authentication in the 5G Radio Access Network (RAN) or other wireless networks and services. Such features can be achieved using cryptographic primitives called Zero-Knowledge Proofs (ZKP). Upon implementing our solution using a state-of-the-art ZKP library and performing several experiments, we provide benchmarks demonstrating that our approach is affordable in speed and memory consumption.
The Bitcoin P2P network is at the core of all communications between clients.\nThe reachable part of this network has been explored and analyzed by numerous\nstudies. Unreachable nodes, however, are, in most part, overlooked.\nNonetheless, they are a relevant part of the network and play an essential role\nin the propagation of messages. In this paper, we focus on transaction\npropagation and show that increasing the participation of unreachable nodes can\npotentially improve the robustness and efficiency of the network. In order to\ndo that, we propose a few changes to the network protocol. Additionally, we\ndesign a novel transaction propagation protocol that explicitly involves\nunreachable nodes to provide better protection against deanonymization attacks.\nOur solutions are simple to implement and can effectively bring immediate\nbenefits to the Bitcoin network.\n
Currently, the data collected by the Internet of Healthcare Things, i.e., healthcare oriented Internet of Things (IoT), still rely on cloud-based centralized data aggregation and processing. To reduce the need for transmission of data to the cloud, the edge computing architecture may be adopted to facilitate machine learning at the edge of the network through leveraging on the amassed computation resources of pervasive IoT devices. In this article, federated learning (FL) is proposed to enable privacy-preserving collaborative model training at the edge of the network across distributed IoT users. However, the users in the FL network may have different willingness to participate (WTP), a hidden information unknown to the model owner. Furthermore, the development of healthcare applications typically requires sustainable user participation, e.g., for the continuous collection of data during which a user’s WTP may change over time. As such, we leverage on the dynamic contract design to consider a two-period incentive mechanism that satisfies the intertemporal incentive compatibility (IIC), such that the self-revealing mechanism of the contract holds across both periods. The performance evaluation shows that our contract design satisfies the IIC constraints and derives greater profits than that of the uniform pricing scheme, thus validating its effectiveness in mitigating the adverse impacts of the information asymmetry.