Blockchain has now become a critical infrastructure in Metaverse for storing and managing the digital resources of users, bridging the real and virtual worlds. However, consensus protocols in blockchains constrain the performance of their applications. While existing voting-based consensus protocols such as HotStuff and other Byzantine Fault Tolerance (BFT) protocols have optimized efficiency and scalability, they simply adopt a one-person-one-vote rule that is not aligned with the human-centric values of most blockchain applications, including Metaverse. Therefore, we propose Stake Voting Protocol (SVP), a secure and scalable consensus protocol, whose design philosophy is to consider validators’ stakes in the BFT protocol and introduce flexibility through a sliding window. We also propose a certification rule within the pipelined two-chain consensus process to enhance security. Furthermore, our epoch change and incentive mechanisms ensure dynamics and liveness, respectively. Finally, our analytical and experimental results demonstrate that the proposed SVP satisfies correctness and can resist specific attacks with low latency and high throughput.

Log-Structured Merge Tree (LSM-Tree) is widely employed in key-value (kv) store owing to its exceptional performance in write-intensive workloads. LSMTree appends kv pairs to memory initially, and only when the memory capacity reaches a threshold does it flush the data to disk. However, in comparison to write, read operations often entail more disk access, resulting in relatively a slower response speed. Although LSM-Tree utilizes an index structure to expedite read operations, its performance enhancement remains limited. In addition, LSM-Tree fails to consider the read hotness of each sorted string table (SSTable) during compaction, leading to significant fluctuations in performance. This paper introduces HL-LSM, a novel LSM-Tree. HL-LSM utilizes learned index to replace original index to save system overhead and improve read performance. Moreover, a lightweight read hotness statistics is devised to optimize the compaction and assess the feasibility of each SSTable in constructing a learned index. In order to evaluate the performance of HL-LSM, we constructed a system prototype, HLDB, based on WiscKey. Experiment demonstrates that in read-intensive scenarios, HLDB is able to reduce the overall system latency by nearly 10% compared to WiscKey. Furthermore, it was observed that the optimization effect of HL-LSM improves as the variance of hotness value distribution increases.

With its wide range of applications, the Internet shows a future trend towards abundant and diverse data resources with multiple types of identifiers (multi-identifiers). However, the legacy Domain Name System (DNS) in the current TCP/IP network architecture has failed to manage these identifiers due to the centralized security issue. While some decentralized DNS alternatives have been proposed, they also face scalability issues. In this paper, we propose a blockchain-based Hierarchical Multi-Identifier System, named H-MIS, as a DNS alternative. Specially, it realizes optimal decentralization and scalability by introducing the Zero-Knowledge rollup (ZK-rollup) solution to synchronize the upper and lower on-chain identifier data, as well as off-chain associated resource data. Finally, we implement H-MIS on Ethereum and evaluate its performance. The experimental results indicate that compared to the original MIS and Ethereum Name Service (ENS), H-MIS has advantages in such aspects as efficiency, data consumption, and Gas fees.

In recent years, blockchain technology has received widespread attention. Smart contracts are programs that run on the blockchain, and their security faces serious challenges for blockchain applications. Inspired by the success of artificial intelligence technology, some smart contract vulnerability detection methods based on deep learning have been proposed and achieved meaningful progress. However, a closer look reveals three flaws in these works. First, some works simply use LSTM modules to perform sequence learning on pre-processing smart contracts, which lacks the ability to extract long-range features and does not support parallel processing of inputs. Secondly, smart contract vulnerability detection methods based on deep learning lack interpretability of results. From the perspective of system design, in order to solve these problems, we propose SmartDT, a more effective, faster, and interpretable smart contract vulnerability detection system. Specifically, (i) we propose an attention-based deep learning smart contract detection module, which is able to learn long-range dependencies in inputs and supports parallel processing of inputs. (ii) After the deep learning module, we stack an optional symbolic execution module for enhancing the interpretability of the classification results. Compared with general symbolic execution detection, our method can achieve faster detection because we can call a specific symbolic analysis model to detect input based on the classification results of the deep learning module. Extensive experiments demonstrate the effectiveness of our proposed method. Compared with other machine learningbased methods, our method achieves better performance and better interpretability, which demonstrates SmartDT’s outstanding feature learning capabilities. Compared with symbolic execution methods, our method achieves faster and more effective detection. In addition, we conducted ablation experiments to verify the effectiveness of each module.

Some Byzantine fault tolerant (BFT) consensus algorithm in consortium blockchains have lots of message broadcast to encroach bandwidth, which greatly affect the efficiency of consensus execution. Although reducing the number of global consensus nodes can help, it is also at the cost of reduced security. Based on the idea of Mimic Defense, this paper proposes a consensus framework for BFT consensus and takes the Parallel Proof of Vote (PPoV) algorithm as an example to design a randomized node sharding and role partitioning scheme to improve security of the consensus process without affecting efficiency much. In addition, the multimode adjudication group composed of the shard leaders can replace the single leader to complete voting statistics to improve the reliability of consensus results. Through theoretical analysis, it is known that the BFT consensus framework based on mimic security, taking PPoV as an example, has a strong defense effect against eclipse attacks and selfish mining. A simulation experiment is also designed to prove that through efficient iteration and dynamic threshold design, the adjudication group greatly improves the reliability of the results and the robustness of the algorithm.

Smart contracts emerged as programs running on the blockchain. Security is one of the major concerns against smart contracts which also exist various vulnerabilities as for any other traditional programs. What was worse, security vulnerabilities in smart contracts may lead to irreversible economic losses. Hence, there is an apparent demand for security audits of contracts before deployment. In recent years, a large number of smart contract vulnerability detection tools have emerged. The methods used by these tools include formal verification, symbolic execution, machine learning, and fuzz testing. These methods can well analyze vulnerabilities, but there are still limitations. In this paper, we optimized and extended the Mythril symbolic execution tool. The optimized pruning algorithm improves the speed of symbolic execution, while the proposed detection algorithm for Transaction Order Dependence vulnerability expands the range of detecting vulnerability. In addition, a machine learning vulnerability detection model is introduced as an auxiliary detection method, which is used to build the complete smart contract vulnerability detection system. The experimental results show that the proposed system reduces the execution time, and improves the accuracy as well as the recall of vulnerability detection compared with the original Mythril tool.

In distributed storage systems, the replication mechanisms are usually used to ensure system reliability and data availability. Random replication is widely used in cloud storage systems to prevent data loss. Copyset Replication (CR) as a replication strategy, makes a nearly optimal trade-off between the number of scattered nodes and the probability of data loss. Compared with random replication, CR greatly reduces the probability of data loss caused by node failure. However, CR's random selection strategy makes it difficult to select the optimal copyset based on data characteristics such as calculation and storage. In response to this problem of CR, the Optimal Copyset Replication (OCR) proposed in this paper can select the optimal copyset according to the specified data characteristics and its corresponding node conditions. Finally, combined with Cyberspace Mimicry Defense (CMD) , we implemented OCR in a distributed object storage system and conducted related experiments. When the calculation type data reaches 300,000, the experimental results prove that compared with CR randomly selecting copyset, OCR reduces the data processing time by nearly 10% through selecting the optimal copyset. By setting relevant parameters, OCR can also ensure that the data distribution of each node is relatively uniform, and avoid data skew.

Each blockchain’s node needs to store a backup of all blocks, resulting in the whole network needs O(n) storage space, which greatly affects the nodes’ scalability. Parallel proof of vote(PPoV) is a permissioned blockchain algorithm that uses block groups as the basic data structures. This paper proposes a data lightweight scheme for PPoV. In the bock group generation stage, the BLS algorithm is used to realize signature aggregation, and the storage space of block signature and vote signature is reduced from O(n) to O(1) without affecting the performance. In the storage stage, we use erasure code to implement storage partition for block groups and ensure the real-time recoverability of complete data. To speed up reading, the timeline-based model applies different storage strategies for hot and cold data. The experimental results show that the empty block group generated by BLS aggregation signature is smaller and less sensitive to the number of nodes. And the reduction ratio of storage space under a large number of transactions can be similar to the number of normal nodes.

Distributed storage systems have been widely used in the field of Big Data, Cloud Computing, and Internet of Things. AONT-RS is a classical information dispersal scheme, which blends an ALL-Or-Noting Transform with Reed-Solomon coding to improve the data security of distributed storage systems. In this paper, we analyze the security vulnerabilities in AONT-RS and propose an optimized scheme called AONTNZZD to enhance data security and computational efficiency. Then, we assess the data security of AONT-NZZD from three aspects of reliability, confidentiality, and recoverability. We further implement the proposed scheme in a distributed object storage system. Finally, we conduct experiments to compare the performance of AONT-NZZD with other dispersal schemes based on AONT-RS. Theoretical analysis and experimental results show that AONT-NZZD outperforms AONT-RS in both security and efficiency.

The logging system records the logs generated by the software so that the administrator can handle the problems that occur. However, the traditional log system is not secure enough and the stored logs are easily falsified. As a decentralized distributed storage technology, the blockchain can ensure that the blockchain network works normally in the presence of a few malicious nodes or failed nodes. So we use the blockchain to store the logs, which improves the security of the log system. In order to improve the performance of the blockchain, we use a voting-based consensus algorithm as a blockchain consistency protocol. This article introduces the architecture and implementation of the log system and verifies the feasibility of the system through experiments.

IPFS [1] is a peer-to-peer version controlled filesystem that synthesizes learnings from many previous successful systems. IPFS combines a distributed Hash table, an incentivized block exchange, and a self-certifying namespace [1]. IPFS is a peer-to-peer hypermedia protocol to make the web faster, safer, and more open. According to the characteristics of IPFS, we propose an improved P2P file system scheme based on IPFS and Blockchain. We address the high-throughput problem for individual users in IPFS by introducing the role of content service providers. Consider data reliability and availability, storage overhead and other issues for service providers, we provide a novel zigzag-based storage model to improve the block storage model that IPFS provides. Moreover, we introduce blockchain to combine IPFS with this storage model. According to analysis, this proposed scheme can effectively solve the above problems.

Distributed storage system has been widely used currently. Compared with traditional NAS and SAN storage, distributed storage system has obvious advantages in terms of cost, performance and security. The security of distributed storage system is mainly reflected in the data redundancy level. However, if there are security risks in the operating system and network environment, the security of the data still cannot be guaranteed. How to fundamentally solve the security risks of distributed storage system is an urgent problem. Based on the theory of mimic defense, Storage Architecture for Mimic Defense(SAMD) is put forward in this paper. In the proposed SAMD, dynamic heterogeneous redundancy function is introduced into distributed storage system. During the process of data reading and writing, the execution results are obtained from dynamic heterogeneous executive units, and the processing and judgement are carried out according to the customized strategy. It then dynamically allocates the executive units and storage nodes to achieve the effect of active defense.

In the era of big data, many tools and algorithms are designed to deal with the increasing data. Because data management on the traditional relational database causes scalability and performance problem, data management across multiple data centers has been proposed. Cassandra is a NoSQL database, which is built to store huge volumes of data and manage data across multiple data centers. Generally, Cassandra assign data to different nodes based on consistent hashing algorithm. So the performance of Cassandra is excellent when most random read and write are requested. However, when the popular data is read or written frequently and the data is distributed to different data centers. Each operation brings the communication delay that could not be ignored. In this article, we propose a scheduling strategy based on multi-queues to reduce communication delay when data are accessed across different data centers. To validate the effectiveness of this strategy, we implemented our approach on Cassandra and evaluation results showed the average response time of data access is reduced across multiple data centers.

As the Internet and the big data system evolve rapidly, the deployment of distributed applications becomes widespread, promoting the development of Distributed File System (DFS). The existing defense technologies for DFS, such as detection or patching, mainly aim to protect the system from known attacks and vulnerabilities. However, it is difficult for those systems to solve the growing security issues from the unknown threats due to their passiveness and hysteresis. In this paper, we propose MDFS, a mimic defense theory based architecture for DFS with the capability to improve the data security. Mimic Defense (MD), a proactive defense embedded in MDFS, emphasizes dynamism, heterogeneity and redundancy. The key benefits of MD are transferring the attack surface as well as increasing the cost of modification.

Ceph is a reliable, scalable, unified distributed storage system, and recently has become one of OpenStack's standard open source storage solutions. For the reason of the low performance, Ceph Filesystem (Cephfs) cannot employ erasure codes directly, especially for binary Reed-Solomon (BRS) codes, whose size of the parity block is larger than that of the data block. To address these problems, we implemented efficient BRS codes, and filled the gap between BRS codes and Cephfs by a simple conversion. In addition to that, an efficient framework consisting of filesystem, cache tier and storage tier was adopted in Ceph to ensure that the file data is finally stored with the erasure coding technology. The experimental results show that such a design spends a small amount of additional cost but obtains much better effects.

As data grows exponentially within data centers, cluster deduplication storage systems face challenges in providing high throughput, high deduplication ratio and load balance. As the key technique, data routing algorithm has a strong impact on the deduplication ratio, throughput and load balance in cluster deduplication storage systems. In this paper, we propose SS-Dedup, a novel stateful data routing algorithm for cluster deduplication storage system which can achieve higher system throughput and good load balance at the cost of deduplication ratio loss and memory space in client servers. SS-Dedup takes advantage of data similarity to increases system throughput with little deduplication ratio loss. Specifically, to decrease network traffic and response time, SS-Dedup maintains LRU caches in client servers to store fingerprints of historical routed chunks for each data server. Our experiment results show that while maintaining good load balance and high deduplication ratio, SS-Dedup takes up much lower network bandwidth and provides higher system throughput.

The data warehouse system Hive has emerged as an important facility for supporting data computing and storage. In particular, RCFile is a tailor-made data placement structure implemented in Hive, which is designed for the data processing efficiency. In this paper, we propose several optimized schemes based on RCFile and introduce EStore, which is an optimized data placement structure that is able to improve the query rate and reduce storage space for Hive. Specifically, it adopts both row-store and column-store in blocks, and further classifies the columns by the frequency of each table-column. Moreover, we also employ the classic RDP code to store files of the data table. We conduct experiments on a real cluster, and the results show that EStore has better features in terms of data query rate and storage space compared with RCFile.

Erasure codes such as Reed-Solomon (RS) codes are widely used to improve data reliability in distributed storage systems. Although erasure codes indeed greatly reduce the storage overhead compared to the replication schemes, it is still very costly in terms of network bandwidth when repairing a failed node. To address such problem, we employ the Zigzag code, a MDS array code with optimal repair property, in the practical system. Specifically, we first build a general system on Hadoop to evaluate the encoding, decoding and repair performance of different codes, and then implement Zigzag codes on our system. The experimental results show that the Zigzag codes coincide with the theoretical findings and has certain advantages. Compared to current HDFS modules that use RS codes, our Zigzag based HDFS implementation shows significant reduction of repair disk I/O and repair bandwidth with the same computation complexity.

Distributed file system has emerged in recent years as an efficient solution to store the large amount of data produced anytime and anywhere. In order to guarantee data reliability, it is necessary to introduce redundancy to the storage systems. Compared to simple replication, practical systems are increasingly adopting erasure codes for better storage efficiency. However, traditional erasure codes such as maximum-distance-separable (MDS) codes, are designed over a large finite field, which inevitably hinders the wide implementation of erasure codes. In this paper, we propose a new family of MDS codes with high computation efficiency. More specifically, only XOR operation is included in the encoding process to generate parity blocks. Upon failure of a storage node, we use the efficient Zigzag decoding method to recover the failed blocks, which achieves the optimal encoding and an efficient decoding. Furthermore, we implement the proposed codes in a distributed file system, and the results show the high performance of the new codes.

Recently, traditional erasure codes such as Reed-Solomon (RS) codes have been increasingly deployed in many distributed storage systems to reduce the large storage overhead incurred by the widely adopted replication scheme. However, these codes require significantly high resources with respect to network bandwidth and disk I/O during recovery of missing or unavailable data. It is referred as the recovery problem. In this paper, we dedicate to integrating exact minimum bandwidth regenerating codes into practical systems to solve the recovery problem. We design an implementation friendly storage code with the recently proposed BASIC framework and ZigZag decodable code for saving recovery bandwidth and disk I/O. We build a system called STORE based on this code and evaluate our prototype atop a HDFS cluster testbed with 21 nodes. As shown in this paper, the recovery bandwidth achieves minimum approximately during recovery of both data block and parity block with STORE. Another attractive result is that the recovery disk I/O also achieves minimum approximately during recovery of data block. Due to the reduction of recovery bandwidth and disk I/O, the degraded read throughput is boosted notably.

Fractional repetition (FR) codes are a special class of regenerating codes characterized by the exact and uncoded repair property. In this work, we propose an explicit method to construct FR codes from combinatorial configurations. The proposed construction gives FR codes with parameters that are not covered by prior approaches.

Regenerating codes (RGC) are a class of distributed storage codes that can provide efficient repair of failure nodes in distributed storage systems. In general, the reduction of repair bandwidth of RGC is at the expense of a small increase in storage cost and computational cost. The high computational complexity of data coding over a finite field of large size makes it unsuitable for practical distributed storage systems. BASIC codes, which stands for Binary Addition and Shift Implementable Convolutional codes, is introduced in [1] with the aim of reducing computational complexity, while retaining the benefits of RGC. In this paper, we present a construction of exact-repair BASIC codes at the minimum-storage point (MSR). A helper node needs no coding to repair a failure node for the minimum-storage BASIC codes. The results of simulation show minimum-storage BASIC codes outperform Cauchy Reed-Solomon codes in both repairing cost and coding cost.

The explosion of big data stored in distributed file systems calls for more efficient storage paradigms. While replication is widely used to ensure data availability, erasure codes provide a much better tradeoff between storage and availability. Reed-Solomon (RS) codes are the standard design choice, however, their high repair cost is often considered an unavoidable price to pay for high storage efficiency and high reliability. BASIC codes can achieve the optimal tradeoff between storage capacity and repair bandwidth with much less complexity of regenerating codes, which is first proposed in [1]. This paper integrate one construction of the minimum storage BASIC (MS-BASIC) codes [2] into a Hadoop HDFS cluster testbed with up to 22 storage nodes. We demonstrate that MS-BASIC codes conform to the theoretical findings and achieve recovery bandwidth saving compared to the conventional recovery approach based on RS codes.