Federated Learning (FL) has emerged as a privacy-preserving distributed Machine Learning paradigm, which collaboratively trains a shared global model across a number of end devices (clients) without exposing their raw data. However, FL typically assumes that all clients are benign and trust the coordinating central server, which is unrealistic for many real-world scenarios. In practice, clients can harm the FL process by sharing poisonous model updates while the server could malfunction or misbehave. Moreover, the deployment of FL for real-world applications is hindered by the high communication overhead between the server and clients that are often at the network edge with limited bandwidth. To address these key challenges, we propose a lightweight Blockchain-Empowered secure and efficient Federated Learning (BEFL) system. BEFL is built by integrating a communication-efficient and mutual-information guarded training scheme, a cost-effective Verifiable Random Function (VRF)-based consensus mechanism, and Inter-Planetary File System (IPFS)-enabled scalable blockchain architecture. Extensive simulation experiments using two benchmark FL datasets demonstrate that BEFL is resistant against byzantine clients launching data poisoning and model poisoning attacks, fault-tolerant against colluded malicious blockchain nodes, scalable to a large number of blockchain nodes, and communication-efficient at the network edge.
Roberto Aparici Marino, Lorenzo Carnevale, Massimo Villari
Federated Learning (FL) is a cutting-edge technology for distributed solving of large-scale problems using local data exclusively. The potential of Federated Learning is nowadays clear in different context from automatic analysis of healthcare data to object recognition in video sources coming from public video streams, from distributed search for data breach and finance frauds to collaborative learning of hand typing on mobile phone. Multi-robot systems can also largely benefit from FL concerning resolution of problems like trajectory prediction, non colliding trajectory generation, distributed localization and mapping or distributed reinforcement learning. In this paper we propose a multi-robot framework that includes distributed learning capabilities by using Decentralized Stochastic Gradient Descent on graphs. First of all we motivate the position of the paper discussing the privacy preserving problem for multi robot systems and the need of decentralized learning. Then we build our methodology starting from a set of prior definitions. Finally we discuss in details the possible applications in robotics field.
Training contemporary AI models requires investment in procuring learning data and computing resources, making the models intellectual property of the owners. Popular model watermarking solutions rely on key input triggers for detection; the keys have to be kept private to prevent discovery, forging, and removal of the hidden signatures. We present ZKROWNN, the first automated end-to-end framework utilizing Zero-Knowledge Proofs (ZKP) that enable an entity to validate their ownership of a model, while preserving the privacy of the watermarks. ZKROWNN permits a third party client to verify model ownership in less than a second, requiring as little as a few KBs of communication.
<ns3:p>Continuous improvement in transportation systems and smart vehicles' appearance make new highly intensive applications. Complex applications need high-performance capabilities, real-time responses, and generate massive amounts of data to process and exchange. This presents the idea of vehicular edge computing (VEC), which is proposed to handle complex applications and satisfy smart vehicle processing requirements. VEC enables computation offloading to an edge server to reduce communication latency, execution cost and energy consumption greatly. However, offloading to another node opens up new vulnerabilities regarding security and privacy. Moreover, trust issues in such an untrustworthy environment need an effective trust management solution and incentive mechanisms to improve overall security. This will increase the computation offloading success rate and the vehicles' willingness to share their resources. Particularly given the high transportability and heterogeneity of vehicular networks, the conventional security and trust management methods are inadequate. Blockchain, the rapidly emerging trend technology, is a unique solution that can help overcome security and privacy issues and meet trust management and incentive mechanism goals. Blockchain’s immutable distributed ledger, traceability, consensus validation system and smart contract features can improve vehicular network security. Although most research is focused on enhancing the performance of computation offloading algorithms, blockchain security solutions in computation offloading scenarios are not fully discussed. Thus, security and trust issues related to computation offloading in VEC environments need more consideration since supporting the new complex vehicular applications is essential. Therefore, this paper provides a review of recent surveys and studies, an overview of VEC, computation offloading and blockchain, in addition to discussing security, privacy and trust in vehicular networks and computation offloading while considering blockchain as a distributed security solution. We propose a new paradigm called blockchain edge of vehicle (BEoV) at the end, which enables several blockchain-based security services for vehicular computation offloading in particular.</ns3:p>
The adoption of the General Data Protection Regulation (GDPR) has resulted in a significant shift in how the data of European Union citizens is handled. A variety of data sharing challenges in scenarios such as smart cities have arisen, especially when attempting to semantically represent GDPR legal bases, such as consent, contracts and the data types and specific sources related to them. Most of the existing ontologies that model GDPR focus mainly on consent. In order to represent other GDPR bases, such as contracts, multiple ontologies need to be simultaneously reused and combined, which can result in inconsistent and conflicting knowledge representation. To address this challenge, we present the smashHitCore ontology. smashHitCore provides a unified and coherent model for both consent and contracts, as well as the sensor data and data processing associated with them. The ontology was developed in response to real-world sensor data sharing use cases in the insurance and smart city domains. The ontology has been successfully utilised to enable GDPR-complaint data sharing in a connected car for insurance use cases and in a city feedback system as part of a smart city use case.
Abstract Achieving efficient and secure sharing of data in the Internet of Vehicles (IoV) is of great significance for the development of smart transportation. Although blockchain technology has great potential to promote data sharing and privacy protection in the context of IoV, the problem of securing data sharing should be payed more attentions. This paper proposes an IoV data sharing scheme based on the hybrid architecture of blockchain and cloud-edge computing. Firstly, to improve protocol’s efficiency, a dual-chain structure empowered by alliance chain is introduced as the model architecture. Secondly, for the space problem characterized by data storage and security, we adopt distributed storage with the help of edge devices. Finally, to both ensure the efficiency of consensus protocol and protect the privacy of vehicles and owners simultaneously, we improve DPoS consensus algorithm to realize the efficient operation of the IoV data sharing model, which is closer to the actual needs of IoV. The comparison with other data sharing models highlights the advantages of this model, in terms of data storage and sharing security. It can be seen that the improved DPoS has high consensus efficiency and security in IoV.
Laasya Bangalore, Mohammad Hossein Faghihi Sereshgi, Carmit Hazay, Muthuramakrishnan Venkitasubramaniam
In this work, we introduce a lightweight secure aggregation protocol that guarantees liveness (i.e., guaranteed output delivery), robust against faulty inputs and security against malicious clients. First, we improve upon prior works in the “star”-like topology network with a central coordinating (also output) party, Bonawitz et al. (ACM CCS 2017) and Bell et al. (ACM CCS 2020), which are not robust against faulty inputs. Recent works, RoFL (Burkhalter et al.) and (concurrent work) ACORN (Bell et al.) show how to rely on zero-knowledge proofs to address such attacks at expense of significantly high computation costs. We also compare our protocol against the PRIO system by Gibbs and Boneh (USENIX 2017) which achieves the same task in an incomparable security model. We benchmark our protocol with implementation and demonstrate its concrete efficiency. Our solution scales to 1000s of clients, requires only a constant number of rounds, outperforms prior work in computational cost, and has competitive communication cost.
In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors.
<p>With the gradual development of Fourth Industrial Revolution technologies, such as artificial intelligence, the Internet of Things, and big data, and the considerable amount of data in mobile networks, low-latency communication and security management are becoming crucial. Blockchain is a data-distributed processing technology that tracks data records to support secure electronic money transactions and data security management in a peer-to-peer environment without the need of a central trusted authority. The data uploaded to the blockchain-shared ledger are immutable, making tracking integrity preservation facile. However, blockchain technology is limited because it is challenging to utilize in the industry owing to its inability to correct data, even when inaccurate data are uploaded. Accordingly, research on blockchain mechanisms that consider privacy-preserving data management is required to commercialize blockchain technology. Previously, off-chain, blacklist, and hard-fork methods have been proposed; however, their application is challenging or impractical. Therefore, to protect privacy, we propose a layered blockchain mechanism that can correct data by adding a buffer blockchain. We evaluated the latency, security, and space complexity of layered blockchains. The security and security-to-latency ratio for data management of the selective layered blockchain is 2.2 and 11.3 times higher than the conventional blockchains, respectively. The proposed selective layered blockchain is expected to promote the commercialization of blockchain technologies in various industries by protecting user privacy.</p> <p>&nbsp;</p>
Nowadays, the utilization of online auction platforms is becoming increasingly prevalent.Online auction provides a common and practical way for global buyers to compete fairly.Nevertheless, the anonymous environment may bring collusion among entities with effects on results.Compared with traditional mechanisms which rely on third-party platforms, the data auction based on smart contract can create a decentralized environment to avoid the occurrence of collusion.Meanwhile, there exists few research on the verification of its reliability and safety which is worth investigating from the perspective of formal methods.In this paper, we apply Process Algebra CSP in modeling the data auction communicating system among five key entities.In addition, we use Process Analysis Toolkit (PAT) to realize the mechanism and verify five crucial properties, including deadlock freedom, data reachability, data correctness, anti-collusion capability and data security.The verification results indicate that the architecture of data auction based on smart contract can satisfy all the above requirements.Especially, the design of asymmetric encryption for the fundamental information ensures the non-occurrence of collusion in the auction.Additionally, the digital signature generated by private key attached to the message guarantees the safety of the interaction.
Recent advancements in digital accident forensics, a conceptual evidence management paradigm developed using smart contracts and interplanetary file system in iov. This paper comprehensively summarizes the Smart contract implementation blockchain framework for vehicle accident investigation in IoV. We investigate comparing some review papers to find the classification of the smart contract. Using blockchain, evidence management provides an immutable and auditable method for investigating and resolving accident cases. Precisely we first investigate the security and privacy threats; therefore, Smart contracts provide effective access control for proof data and reports. On both the public and private Ethereum blockchains, the cost of setting up and executing transactions using smart contracts is assessed. However, we utilized the Inter Planetary File System most efficiently while minimizing memory and execution costs. Finally, we draw open research directions for building future digital-proof management.
The exponential growth of Big Data has heightened concerns surrounding privacy, security, and data ownership. Traditional centralized models often struggle to provide scalable and resilient privacy assurances. Distributed Ledger Technologies (DLTs) such as blockchain offer decentralized frameworks that enhance privacy, integrity, and control over Big Data assets. This article explores the potential of decentralized privacy solutions by examining the integration of DLTs into Big Data ecosystems. We discuss emerging frameworks, key technological innovations, and challenges in adoption. Graphical analysis further highlights trends in adoption and security improvements.
Aditya Pribadi Kalapaaking, Ibrahim Khalil, Mohammed Atiquzzaman
The Internet of Things (IoT) is revolutionizing numerous industrial applications by employing smart devices in manufacturing and industrial processes. Industries based on IoT generate extensive data, typically analyzed using various machine learning (ML) models. Federated learning (FL) is an emerging, privacy-preserving ML method where clients train models locally and develop a global model based on the aggregation of local models, without sharing the local data set with a third party. However, FL methods struggle to achieve trustworthiness and incorporate accountable ML principles. Blockchain technologies are being developed across different industries to enhance trust and security. This article proposes a blockchain-enabled, verifiable model for securing FL within IoT systems. Our proposed framework combines a trusted execution platform (TEE) to secure each client’s local model training process, and multisignature-powered global model verification to ensure ML model verifiability. We conducted several experiments with different data sets to assess our proposed framework. The experiments demonstrated the high efficiency and scalability of the proposed framework.
Ferenc Béres, István András Seres, Domokos M. Kelen, András A. Benczúr
Network-level privacy is the Achilles heel of financial privacy in cryptocurrencies. Financial privacy amounts to achieving and maintaining blockchain- and network-level privacy. Blockchain-level privacy recently received substantial attention. Specifically, several privacy-enhancing technologies were proposed and deployed to enhance blockchain-level privacy. On the other hand, network-level privacy, i.e., privacy on the peer-to-peer layer, has seen far less attention and development. In this work, we aim to provide a peer-to-peer network simulator, ethp2psim, that allows researchers to evaluate the privacy guarantees of privacy-enhanced broadcast and message routing algorithms. Our goal is two-fold. First, we want to enable researchers to implement their proposed protocols in our modular simulator framework. Second, our simulator allows researchers to evaluate the privacy guarantees of privacy-enhanced routing algorithms. Finally, ethp2psim can help choose the right protocol parameters for efficient, robust, and private deployment.
Distributed Ledger Technologies (DLTs) and blockchain systems are used in various higher-level departments, government sectors and commercial industries. This article reviews how DLTs and blockchain systems work with IOT devices and how it provides security and scalability. The metaverse sets a new standard for social media sites and 3D virtual spaces. Moreover, the key aim of the virtual world is to safeguard the metadata of IOT customers. Additionally, crypto is an effective solution due to its openness, data integrity, and accountability characteristics. So, we review the two new burning technologies of crypto and the virtual world from a methodological perspective, i.e. data collection, saving data, allocation, integration, and data confidentiality are all aspects of data management. By each strategy, in this article, we discuss the methodological techniques of the meta chain and then investigate the potential benefits of blockchain technology. Further, we analyze how blockchain will influence other critical enabling technologies in the metaverse's service world, such as the IOT.
Chengzu Dong, Jingwen Zhou, Qi An, Frank Jiang · 7 authors
In recent years, edge-based intelligent UAV delivery systems have attracted significant interest from both the academic and industrial sectors. One key obstacle faced by these smart UAV delivery systems is data privacy, as they rely on vast amounts of data from users and UAVs for training machine learning models for person re-identification (ReID) purposes. To tackle this issue, federated learning (FL) has been extensively adopted as a promising solution since it only involves sharing and updating model parameters with a central server, without transferring raw data. However, traditional FL still suffers from the problem of having a single point of failure. In this study, we present a performance optimization method for federated person re-identification using benchmark analysis in blockchain-powered edge-based smart UAV delivery systems. Our method integrates a decentralized FL mechanism enabled by blockchain, which eliminates the necessity for a central server and stores private data on a decentralized permissioned blockchain, thus preventing a single point of failure. We employ the person ReID application in intelligent UAV delivery systems as a representative example to drive our research and examine privacy concerns. Additionally, we introduce the Federated Re-identification Consensus (FRC) protocol to address the scalability issue of the blockchain in supporting UAV delivery systems. The efficiency of our proposed method is illustrated through experiments on energy efficiency, confirmation time, and throughput. We also explore the effects of the incentive mechanism and analyze the system’s resilience under various security attacks. This study offers valuable insights and potential solutions for addressing data privacy and security challenges in the fast-growing domain of smart UAV delivery systems.
Vehicular ad hoc networks (VANETs) are used for improving traffic efficiency and road safety. However, VANETs are vulnerable to various attacks from malicious vehicles. Malicious vehicles can disrupt the normal operation of VANET applications by broadcasting bogus event messages that may cause accidents, threatening people's lives. Therefore, the receiver node needs to evaluate the authenticity and trustworthiness of the sender vehicles and their messages before acting. Although several solutions for trust management in VANETs have been proposed to address these issues of malicious vehicles, existing trust management schemes have two main issues. Firstly, these schemes have no authentication components and assume the nodes are authenticated before communicating. Consequently, these schemes do not meet VANET security and privacy requirements. Secondly, existing trust management schemes are not designed to operate in various contexts of VANETs that occur frequently due to sudden variations in the network dynamics, making existing solutions impractical for VANETs. In this paper, we present a novel blockchain-assisted privacy-preserving and context-aware trust management framework that combines a blockchain-assisted privacy-preserving authentication scheme and a context-aware trust management scheme for securing communications in VANETs. The authentication scheme is proposed to enable anonymous and mutual authentication of vehicular nodes and their messages and meet VANET efficiency, security, and privacy requirements. The context-aware trust management scheme is proposed to evaluate the trustworthiness of the sender vehicles and their messages, and successfully detect malicious vehicles and their false/bogus messages and eliminate them from the network, thereby ensuring safe, secure, and efficient communications in VANETs. In contrast to existing trust schemes, the proposed framework can operate and adapt to various contexts/scenarios in VANETs while meeting all VANET security and privacy requirements. According to efficiency analysis and simulation results, the proposed framework outperforms the baseline schemes and demonstrates to be secure, effective, and robust for enhancing vehicular communication security.
Abstract The goal of a content delivery network (CDN) is to reduce the content delivery latency to end-users by using distributed cache servers. Nevertheless, it is very expensive to deploy and maintain cache servers in a large-scale. To solve this problem, CDN providers have come up with a new content delivery strategy: allowing end-users's IoT edge devices to share their storage/bandwidth resources. This new edge CDN platform needs to address two core questions: (1) how can we incentivize end users to share IoT devices? (2) how can we facilitate a safe and transparent content transaction environment for end users? In this paper, we introduce SmartSharing, a new content delivery network solution. In smartSharing, the over-the-top (OTT) IoT devices belonging to end-users are used as mini-cache servers. To motivate end users to share the idle devices and storage/bandwidth resources, SmartSharing designs the content delivery schedule and the pricing scheme based on game theory and machine learning algorithms (to be specific, a tailored Expectation-Maximization (EM) algorithm). To facilitate content trading among end users, SmartSharing creates a secure and transparent transaction platform based on smart contracts in Ethereum. In addition, SmartSharing's performance evaluation not only through trace-driven simulations in the real world, but also a prototype using content metadata and the achieved pricing schemes. The evaluation results show that CDN providers, end users and content providers can all benefit from our SmartSharing framework.
Long Zhang, Gang Feng, Shuang Qin, Xiaoqian Li · 6 authors
Blockchain is envisioned as one of the promising technologies to address trust concern brought by mobile crowdsensing (MCS), due to its auditability, immutability and decentralization. Nevertheless, blockchain cannot fundamentally guarantee that the valuable sensed data outside the chain can enter the chain, although data integrity and consistency can be ensured once it is confirmed inside the chain. In addition, simply applying blockchain in MCS while ignoring possible abnormal saboteurs hidden in numerous devices may mislead the normal operation of blockchain, resulting in untrustworthy interactions. Consequently, it is highly desirable to build a trust-preserving mechanism (TPM) to fully enjoy the benefits of using blockchain in MCS. To this end, we first resort to a probabilistic trust assessment inferred from the interaction outcomes in blockchain, to incentivize participants to maintain the trustworthiness of interactions. By inferring trust to aid decision-making, trust decision is further made, including leader election and transaction data generation, to filter untrusted nodes from participating in blockchain process. Finally, extensive simulations are conducted to validate the effectiveness and efficiency of TPM, and improve the performance in terms of contribution rate, consensus accuracy and system stability.
Xiaowan Wang, Huiyin Xie, Shan Ji, Liang Liu · 5 authors
The rapid development of the Internet and Internet of Things has rapidly introduced human society into the information age, and the way of fake news production has been updated, which has greatly affected the normal life of human beings. In order to identify worthless fake news and trace massive fake news data from unknown sources, and share valuable news data to fully disseminate effective real news, news owners usually store news data in cloud. Users of IoT terminals can access news data on demand without storing it locally. However, the authenticity of the fictive newspaper numbers source, which is easy to destroy, and the social media platform. Besides, when massive news data is saved on cloud server, the news owners have to at the risk of lose physical control over news data and it will face the risk of fake news being disseminated and real news being falsified. Thus, this paper proposes a novel mechanism for secure storage of news data using blockchain technology. Firstly, traceability and verification of fake news data is improved by the cooperative storage model on and off the chain. Secondly due to the inability of past polynomial commitment to update the commitment, we will be a hindrance to use polynomial commitment to build a secure authentication protocol. Therefore, in this paper, we design the update algorithm for polynomial commitment in order to be able to guarantee the consistency of on-chain and blockchain database news data.
Blockchain technology has become wide usage technology that can be integrated to variety of applications in different sectors to enhance the performance, security or to add a layer of implementation with specific features. In some cases it replaces the traditional type of existed systems to provide a solution to specific concerns such as the case with land record system. In this research, we provide a brief introduction of the blockchain technology in land administration, analyzing some of existed and proposed frameworks for land administration systems through a systematic review and summarize the results. Also, we highlighted the main benefits of the blockchain technology and the most important vulnerabilities in blockchain platforms. Also, we proposed a private blockchain framework using Hyper- ledger Fabric and highlighted the main reasons to choose such a platform for our system and how it can solve the double spending and tampering issues. Finally, the objective of this research is to provide mechanisms that solve the security issues to answer the research questions and develop and verify the effectiveness of our proposed framework.
The rapid digital revolution in recent decades has resulted in an overwhelming amount of information, particularly in the realm of modern education systems and related materials. This phenomenon, often referred to as information overload, necessitates the development of educational systems that can effectively search, classify, and categorize this vast amount of available information. Of utmost importance for such educational information systems is the safeguarding of personal data, which refers to information that can identify an individual or their family. School records, for example, contain various types of personal data such as the individual’s name, address, contact details, disciplinary history, as well as their grades and progress checks. Even if individuals choose to make this data public, it remains inherently personal. Another category of data involves more sensitive topics such as student biometrics (e.g. fingerprints, photographs), religious beliefs, health information (e.g. allergies), or dietary restrictions, which may imply religious or health-related aspects. Processing data in this category can pose risks to individuals; hence, strict rules and appropriate consent are necessary to ensure their protection. To address these challenges, this research paper proposes a zero-knowledge proof intelligent recommendation system designed to protect students’ data privacy in the digital age. The proposed method incorporates an Intelligent Recommendation System (IRS) that utilizes an optimized version of the Matrix Factorization technique, calculated as an Eulerian Walk chart. Furthermore, the Schnorr Zero-Knowledge Proof format, based on the discrete logarithm problem, ensures the privacy of personal data during message exchange between educational entities.
With natural language processing as an important research direction in deep learning, the problems of text similarity calculation, natural language inference, question and answer systems, and information retrieval can be regarded as text matching applications for different data and scenarios. Secure matching computation of text string patterns can solve the privacy protection problem in the fields of biological sequence analysis, keyword search, and database query. In this paper, we propose an Intelligent Semi-Honest System (ISHS) for secret matching against malicious adversaries. Firstly, a secure computation protocol based on the semi-honest model is designed for the secret matching of text strings, which adopts a new digital encoding method and an ECC encryption algorithm and can provide a solution for honest participants. The text string matching protocol under the malicious model which uses the cut-and-choose method and zero-knowledge proof is designed for resisting malicious behaviors that may be committed by malicious participants in the semi-honest protocol. The correctness and security of the protocol are analyzed, which is more efficient and has practical value compared with the existing algorithms. The secure text matching has important engineering applications.