Existing blockchain systems can quickly respond to verifiable primary key queries based on authenticated indexes. However, many blockchain applications also require high-performance queries on non-primary keys. For example, traders query NFT or tokenized RWA with certain features, e.g., type and return. Therefore, it necessitates authenticated secondary indexes to support efficient verifiable queries on non-primary keys. However, the existing approach to authenticated index design that couples index and authenticated digest together does not adapt well to the phased nature of non-primary key queries, making the most time-consuming process of commitment generation severely block the query process. In this study, we propose the first authenticated secondary index MEST for verifiable non-primary key queries. MEST decouples the data index and authenticated digest, which can parallelize commitment generation on the secondary index and the query processing on the primary index, thus greatly reducing the latency of the non-primary key query. Furthermore, we adopt an Extendible Hash Table to index data and propose a Merkle Growth Tree to generate commitment, which can dynamically adapt to the rapid growth of data and the skew in data access pattern. Extensive experiments on both synthetic and real datasets demonstrate that MEST improves throughput by 3.17×, reduces latency by 59%, and exhibits better scalability than baselines.

Deploying machine learning (ML) inference pipelines in databases become increasingly prevalent in many applications. In order to avoid data transfer between the database and ML runtimes, existing ML2SQL frameworks parse ML pipelines to a graph consisting of ML operators and then translate it into pure SQL. Nevertheless, they typically rewrite the graph without operator fusion or only consider the fusion between certain operators such as StandardScaler and tree inference. However, there are various operators in ML pipelines, which have rich fusion opportunities between each other. To fully exploit operator fusion for graph rewriting, we classify widely used ML operators and design fusion rules driven by their characteristics. Moreover, rewriting the original graph by fusion rules produces candidate graphs that generate SQLs with different execution time. We employ an enumeration-based strategy to search for the graph with the lowest cost. However, this strategy may suffer from the combination explosion on search space for complex ML pipelines. To reduce this space, we propose a greedy-based strategy by exploiting the independence among ML operators. We implement a novel ML2SQL framework as a portable plugin for databases, namely Craftsman. Our experimental evaluations show that, in comparison to the existing approaches, Craftsman generates efficient SQL queries which achieves an average speedup of 2.9x on popular databases such as DuckDB.

Smart contracts have expanded blockchain applications, but permissioned blockchain systems face severe through-put challenges, especially with the increasing complexity of nested contract transactions. These transactions, involving cross-contract interactions and deep call chains, intensify execution conflicts and rollback overhead, ultimately limiting parallelism. We propose Loom, a deterministic execution framework that enhances the efficiency of nested contract transactions. Loom employs snapshot-based concurrent pre-execution to decompose transactions into fine-grained subtransactions. To reduce rollback overhead, it introduces a two-phase rollback algorithm to minimize computational redundancy and fine-grained rescheduling to improve subtransaction-level parallelism during re-execution. Additionally, a multi-phase parallelism mechanism optimizes resource utilization across transaction blocks. Experimental results show that Loom achieves 6.1 × to$10.2\times$higher throughput while reducing rollback overhead by 89.9% to 98.4%, significantly outperforming state-of-the-art solutions.

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.

The current blockchain system suffers from serious scalability bottleneck, which greatly limits the application in large-scale. Furthermore, with the emergence of high-throughput consensus algorithms in permissioned blockchain, how to efficiently execute smart contracts becomes a critical challenge. To solve this issue, a two-phase concurrent execution mechanism has been adopted recently, where the primary executes a batch of transactions concurrently in the first phase, then the rest replays them in the second phase to achieve consistency. However, these works only enable intra-node concurrency, not inter-node concurrency. This demonstration showcases SEFrame, a novel execution framework for smart contracts of permissioned blockchain to achieve intra- and inter-node concurrency with the confidentiality guarantee of Intel Software Guard Extensions (SGX). We use real-time dashboards containing the output of SEFrame, which allows attendees to interactively explore how SEFrame achieves efficient inter- and intra-node concurrency.

Although the emergence of the programmable smart contract makes blockchain systems easily embrace a wide range of industrial services, how to execute smart contracts efficiently becomes a big challenge nowadays. Due to the existence of Byzantine nodes, existing mature concurrency control protocols in database cannot be employed directly, since the mechanism of executing smart contracts varies a lot. Furthermore, even though smart contract execution follows a two-phase style, i.e., the primary node executes a batch of smart contracts in the first phase and the validators replay them in the second phase, existing parallel solutions merely focus on the optimization for the first phase, rather than the second phase. In this paper, we propose a novel two-phase concurrency control protocol to optimize both phases for the first time. First, the primary executes transactions in parallel and generates a transaction dependency graph with high parallelism for validators. Then, a graph partition algorithm is devised to divide the original graph into several sub-graphs to preserve parallelism and reduce communication cost remarkably. Finally, we propose a deterministic replay protocol to re-execute the primary’s parallel schedule concurrently. Moreover, this two-phase protocol is further optimized by integrating with PBFT. Theoretical analysis and extensive experimental results illustrate that the proposed scheme outperforms state-of-art solutions significantly.

Since there are no security concerns such as Sybil attacks, selfish mining, etc., the higher the system throughput, the better for the permissioned blockchain. And with the emergence of consensus algorithms, the throughput rates of permissioned blockchain can be up to thousands of transactions per second. The existing serial execution method for smart contracts becomes a new bottleneck for the system. Due to the lack of mutual trust between nodes, for a batch of smart contracts contained in a block, the traditional two-phase smart contract concurrency approach can only achieve concurrency within a single node, but not the parallel execution of contracts between nodes. In this paper, we propose a new two-phase framework based on trusted hardware Intel SGX, which can avoid the re-execution of all smart contracts on all nodes and improve parallelism between nodes. And consistency between nodes is achieved directly with state replication, rather than by re-executing transactions. We design a pre-execution mechanism for smart contracts in untrusted memory to batch fetch all the state data that a smart contract needs to access to reduce frequent enclave transitions during smart contract execution. Besides, we propose a method that generates a compact read-write set and a data structure named Merkle Forest which can generate the compact Merkle multiproofs for the initial data in untrusted memory in parallel and can quickly verify the correctness of the data passed in the enclave. Finally, we integrate all the techniques proposed in this paper into an open-source system BFT-SMaRt to evaluate our approach in a distributed setting. Experimental results show the efficiency of the proposed methods.

The full-replication data storage mechanism, as commonly utilized in existing blockchains, suffers from poor scalability, since it requires every node to preserve a complete copy of the whole block data locally to tolerant potential Byzantine failures. In a hostile environment, the malicious node may discard or tamper data deliberately. Thus, existing distributed storage method, which partitions data into multiple parts and distributes them over all nodes, cannot suit for blockchains. This demonstration showcases BFT-Store, a novel distributed storage engine for blockchains to break full-replication by integrating erasure coding with Byzantine Fault Tolerance (BFT) consensus protocol. This demonstration will (\romannumeral1) allow audience members to see how BFT-Store partitions block data over all nodes to reduce the storage occupation of system, and (\romannumeral2) allow audience members to see how BFT-Store recovers blocks under distributed scenario even with Byzantine failure.

We demonstrate SChain, a consortium blockchain that scales transaction processing to support large-scale enterprise applications. The unique advantage of SChain stems from the exploitation of both intra- and inter-block concurrency. The intra-block concurrency not only takes advantage of the multi-core processor on a single peer but also leverages the capacity of multiple peers. The interblock concurrency enables simultaneous processing across multiple blocks to increase the utilization of various peers. In our demonstration, we use real-time dashboards containing visualization based on the output of SChain to give the attendees interactive explorations of how SChain achieves intra- and inter-block concurrency.

The full-replication data storage mechanism, as commonly utilized in existing blockchains, is the barrier to the system's scalability, since it retains a copy of entire blockchain at each node so that the overall storage consumption per block is O(n) with n participants. Yet another drawback is that this mechanism may limit the throughput in permissioned blockchain. Moreover, due to the existence of Byzantine nodes, existing partitioning methods, though widely adopted in distributed systems for decades, cannot suit for blockchain systems directly, so that it is critical to devise new storage mechanism for blockchain systems. This article proposes a novel storage engine, called BFT-Store, to enhance storage scalability by integrating erasure coding with Byzantine Fault Tolerance (BFT) consensus protocol. The first property of BFT-store is that the storage consumption per block can be reduced to O(1) for the first time, which enlarges overall storage capability when more nodes attend the blockchain. Second, we design an efficient online re-encoding protocol for storage scale-out and a hybrid replication scheme to enhance reading performance. Analysis in theory and extensive experimental results illustrate the scalability, availability and efficiency of BFT-Store via the implementation in an open-source permissioned blockchain Tendermint.

In this demo, we present SEBDB, a novel blockchain database that integrates immutability and transparency properties of blockchain with modeling and query ability of relational database. In summary, SEBDB has the following advantages: First, it adopts the linked structure and full replication of data among multiple participants to guarantee immutability and transparency. Second, it introduces the relational model to blockchain without introducing extra overhead, based on which relational queries are supported. SEBDB supports SQL-like language as the general interface to support convenient application development, in which intrinsic operations are re-defined and re-implemented to suit for blockchain platform. Third, it supports rich verifiable queries based on the proposed authenticated index, thin clients can participate in the system regardless of limitations of storage, network, and computing resources. We demonstrate the usability and scalability of SEBDB using a donation system.

The full-replication data storage mechanism, as commonly utilized in existing blockchain systems, is lack of sufficient storage scalability, since it reserves a copy of the whole block data in each node so that the overall storage consumption per block is O(n) with n nodes. Moreover, due to the existence of Byzantine nodes, existing partitioning methods, though widely adopted in distributed systems for decades, cannot suit for blockchain systems directly, thereby it is critical to devise a new storage mechanism. This paper proposes a novel storage engine, called BFT-Store, to enhance storage scalability by integrating erasure coding with Byzantine Fault Tolerance (BFT) consensus protocol. First, the storage consumption per block can be reduced to O(1), which enlarges overall storage capability when more nodes join blockchain. Second, an efficient online re-encoding protocol is designed for storage scale-out and a hybrid replication scheme is employed to improve reading performance. Last, extensive experimental results illustrate the scalability, availability and efficiency of BFT-Store, which is implemented on an open-source permissioned blockchain Tendermint.

Blockchain has been adopted in many applications to construct trust among multiple participants, such as supply chain management, digital assets transfer, philanthropy, etc. Blockchain platforms are often used as decentralized databases. However, existing blockchain platforms are far less convenient to use than traditional databases. They are lack of the capability of modelling complex tasks conveniently and efficiently, especially when both on-chain and off-chain data are involved at the same time. In this paper, we propose and implement a novel blockchain database, called SEBDB, which leverages the existing databases' functionality which are optimized for decades. Comparing to existing works, SEBDB is the first platform which considers both useability and scalability. Specifically, first, weaddrelationaldata semantics into blockchain platform, where each transaction is a tuple with multiple attributes in a pre-defined table. Second, we use SQL-like language as the general interface, instead of code-level APIs, to support convenient application development, in which intrinsic operations are re-defined and re-implemented to suit for blockchain platform. Third, as RDBMS has achieved great success in the past decades, our system, though not relying on RDBMS, treats it as an important component. Finally, we define a mini-benchmark to evaluate the performance of the blockchain database. Extensive experiments demonstrate the effectiveness and efficiency of our proposed system.

Finding matching customers for a given product based on individual user's preference is critical for many applications, especially in e-commerce. Recently, the reverse top- k query is proposed to return a number of customers who regard a given product as one of the k most favorite products based on a linear model. Although a few "hot" products can be returned to some customers via reverse top- k query, a large proportion of products (over 90%, as our example illustrates, see Figure 2) cannot find any matching customers. Inspired by this observation, we propose a new kind of query (R- k Ranks) which finds for a given product, the top- k customers whose rank for the product is highest among all customers, to ensure 100% coverage for any given product, no matter it is hot or niche . Not limited to e-commerce, the concept of customer - product can be extended to a wider range of applications, such as dating and job-hunting. Unfortunately, existing approaches for reverse top- k query cannot be used to handle R- k Ranks conveniently due to infeasibility of getting enough elements for the query result. Hence, we propose three novel approaches to efficiently process R- k Ranks query, including one tree-based method and two batch-pruning-based methods. Analysis of theoretical and experimental results on real and synthetic data sets illustrates the efficacy of the proposed methods.

Microblogs, a mixture of new media and social networks, is a hotbed of lurking users. It is meaningful to capture profiles for a lurking user in customized applications because a lurking user can receive all messages except for sending few messages in microblogs. However, it is difficult to capture profiles for a lurking user because of lacking its user-generated contents. In this paper, we propose an approach to generate the lurking user's profiles by its followees' activities. In addition, we present a unified social context graph model to represent the lurking user's followees' activities. And the RWR algorithm is used to generate profiles of the lurking user in this graph model. Extensive experiments show that our approach can effectively determine profiles for lurking users.