Frontiers of Computer Science最新文献

In this work, we propose a stateless blockchain called CompactChain, which compacts the entire state of the UTXO (Unspent Transaction Output) based blockchain systems into two RSA accumulators. The first accumulator is called Transaction Output (TXO) commitment which represents the TXO set. The second one is called Spent Transaction Output (STXO) commitment which represents the STXO set. In this work, we discuss three algorithms: (i) To update the TXO and STXO commitments by the miner. The miner also provides the proofs for the correctness of the updated commitments; (ii) To prove the transaction’s validity by providing a membership witness in TXO commitment and non-membership witness against STXO commitment for a coin being spent by a user; (iii) To update the witness for the coin that is not yet spent; The experimental results evaluate the performance of the CompactChain in terms of time taken by a miner to update the commitments and time taken by a validator to verify the commitments and validate the transactions. We compare the performance of CompactChain with the existing state-of-the-art works on stateless blockchains. CompactChain shows a reduction in commitments update complexity and transaction witness size which inturn reduces the mempool size and propagation latency without compromising the system throughput (Transactions per second (TPS)).

With the widespread use of network infrastructures such as 5G and low-power wide-area networks, a large number of the Internet of Things (IoT) device nodes are connected to the network, generating massive amounts of data. Therefore, it is a great challenge to achieve anonymous authentication of IoT nodes and secure data transmission. At present, blockchain technology is widely used in authentication and s data storage due to its decentralization and immutability. Recently, Fan et al. proposed a secure and efficient blockchain-based IoT authentication and data sharing scheme. We studied it as one of the state-of-the-art protocols and found that this scheme does not consider the resistance to ephemeral secret compromise attacks and the anonymity of IoT nodes. To overcome these security flaws, this paper proposes an enhanced authentication and data transmission scheme, which is verified by formal security proofs and informal security analysis. Furthermore, Scyther is applied to prove the security of the proposed scheme. Moreover, it is demonstrated that the proposed scheme achieves better performance in terms of communication and computational cost compared to other related schemes.

Federated learning (FL) has emerged to break data-silo and protect clients’ privacy in the field of artificial intelligence. However, deep leakage from gradient (DLG) attack can fully reconstruct clients’ data from the submitted gradient, which threatens the fundamental privacy of FL. Although cryptology and differential privacy prevent privacy leakage from gradient, they bring negative effect on communication overhead or model performance. Moreover, the original distribution of local gradient has been changed in these schemes, which makes it difficult to defend against adversarial attack. In this paper, we propose a novel federated learning framework with model decomposition, aggregation and assembling (FedDAA), along with a training algorithm, to train federated model, where local gradient is decomposed into multiple blocks and sent to different proxy servers to complete aggregation. To bring better privacy protection performance to FedDAA, an indicator is designed based on image structural similarity to measure privacy leakage under DLG attack and an optimization method is given to protect privacy with the least proxy servers. In addition, we give defense schemes against adversarial attack in FedDAA and design an algorithm to verify the correctness of aggregated results. Experimental results demonstrate that FedDAA can reduce the structural similarity between the reconstructed image and the original image to 0.014 and remain model convergence accuracy as 0.952, thus having the best privacy protection performance and model training effect. More importantly, defense schemes against adversarial attack are compatible with privacy protection in FedDAA and the defense effects are not weaker than those in the traditional FL. Moreover, verification algorithm of aggregation results brings about negligible overhead to FedDAA.

A great many practical applications have observed knowledge evolution, i.e., continuous born of new knowledge, with its formation influenced by the structure of historical knowledge. This observation gives rise to evolving knowledge graphs whose structure temporally grows over time. However, both the modal characterization and the algorithmic implementation of evolving knowledge graphs remain unexplored. To this end, we propose EvolveKG–a general framework that enables algorithms in the static knowledge graphs to learn the evolving ones. EvolveKG quantifies the influence of a historical fact on a current one, called the effectiveness of the fact, and makes knowledge prediction by leveraging all the cross-time knowledge interaction. The novelty of EvolveKG lies in Derivative Graph–a weighted snapshot of evolution at a certain time. Particularly, each weight quantifies knowledge effectiveness through a temporarily decaying function of consistency and attenuation, two proposed factors depicting whether or not the effectiveness of a fact fades away with time. Besides, considering both knowledge creation and loss, we obtain higher prediction accuracy when the effectiveness of all the facts increases with time or remains unchanged. Under four real datasets, the superiority of EvolveKG is confirmed in prediction accuracy.

Spreadsheets are very common for information processing to support decision making by both professional developers and non-technical end users. Moreover, business intelligence and artificial intelligence are increasingly popular in the industry nowadays, where spreadsheets have been used as, or integrated into, intelligent or expert systems in various application domains. However, it has been repeatedly reported that faults often exist in operational spreadsheets, which could severely compromise the quality of conclusions and decisions based on the spreadsheets. With a view to systematically examining this problem via survey of existing work, we have conducted a comprehensive literature review on the quality issues and related techniques of spreadsheets over a 35.5-year period (from January 1987 to June 2022) for target journals and a 10.5-year period (from January 2012 to June 2022) for target conferences. Among other findings, two major ones are: (a) Spreadsheet quality is best addressed throughout the whole spreadsheet life cycle, rather than just focusing on a few specific stages of the life cycle. (b) Relatively more studies focus on spreadsheet testing and debugging (related to fault detection and removal) when compared with spreadsheet specification, modeling, and design (related to development). As prevention is better than cure, more research should be performed on the early stages of the spreadsheet life cycle. Enlightened by our comprehensive review, we have identified the major research gaps as well as highlighted key research directions for future work in the area.

Estimating rigid transformation using noisy correspondences is critical to feature-based point cloud registration. Recently, a series of studies have attempted to combine traditional robust model fitting with deep learning. Among them, DHVR proposed a hough voting-based method, achieving new state-of-the-art performance. However, we find voting on rotation and translation simultaneously hinders achieving better performance. Therefore, we proposed a new hough voting-based method, which decouples rotation and translation space. Specifically, we first utilize hough voting and a neural network to estimate rotation. Then based on good initialization on rotation, we can easily obtain accurate rigid transformation. Extensive experiments on 3DMatch and 3DLoMatch datasets show that our method achieves comparable performances over the state-of-the-art methods. We further demonstrate the generalization of our method by experimenting on KITTI dataset.

We consider GROUP CONTROL BY ADDING INDIVIDUALS (GCAI) in the setting of group identification for two procedural rules—the consensus-start-respecting rule and the liberal-start-respecting rule. It is known that GCAI for both rules are NP-hard, but whether they are fixed-parameter tractable with respect to the number of distinguished individuals remained open. We resolve both open problems in the affirmative. In addition, we strengthen the NP-hardness of GCAI by showing that, with respect to the natural parameter the number of added individuals, GCAI for both rules are W[2]-hard. Notably, the W[2]-hardness for the liberal-start-respecting rule holds even when restricted to a very special case where the qualifications of individuals satisfy the so-called consecutive ones property. However, for the consensus-start-respecting rule, the problem becomes polynomial-time solvable in this special case. We also study a dual restriction where the disqualifications of individuals fulfill the consecutive ones property, and show that under this restriction GCAI for both rules turn out to be polynomial-time solvable. Our reductions for showing W[2]-hardness also imply several algorithmic lower bounds.

Hybrid memory systems composed of dynamic random access memory (DRAM) and Non-volatile memory (NVM) often exploit page migration technologies to fully take the advantages of different memory media. Most previous proposals usually migrate data at a granularity of 4 KB pages, and thus waste memory bandwidth and DRAM resource. In this paper, we propose Mocha, a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically, but manages them in a cache/memory hierarchy. Since the commercial NVM device-Intel Optane DC Persistent Memory Modules (DCPMM) actually access the physical media at a granularity of 256 bytes (an Optane block), we manage the DRAM cache at the 256-byte size to adapt to this feature of Optane. This design not only enables fine-grained data migration and management for the DRAM cache, but also avoids write amplification for Intel Optane DCPMM. We also create an Indirect Address Cache (IAC) in Hybrid Memory Controller (HMC) and propose a reverse address mapping table in the DRAM to speed up address translation and cache replacement. Moreover, we exploit a utility-based caching mechanism to filter cold blocks in the NVM, and further improve the efficiency of the DRAM cache. We implement Mocha in an architectural simulator. Experimental results show that Mocha can improve application performance by 8.2% on average (up to 24.6%), reduce 6.9% energy consumption and 25.9% data migration traffic on average, compared with a typical hybrid memory architecture–HSCC.

Protein acetylation refers to a process of adding acetyl groups (CH3CO-) to lysine residues on protein chains. As one of the most commonly used protein post-translational modifications, lysine acetylation plays an important role in different organisms. In our study, we developed a human-specific method which uses a cascade classifier of complex-valued polynomial model (CVPM), combined with sequence and structural feature descriptors to solve the problem of imbalance between positive and negative samples. Complex-valued gene expression programming and differential evolution are utilized to search the optimal CVPM model. We also made a systematic and comprehensive analysis of the acetylation data and the prediction results. The performances of our proposed method aie 79.15% in S_p, 78.17% in S_n, 78.66% in ACC 78.76% in F1, and 0.5733 in MCC, which performs better than other state-of-the-art methods.

Abstract

BERT is a representative pre-trained language model that has drawn extensive attention for significant improvements in downstream Natural Language Processing (NLP) tasks. The complex architecture and massive parameters bring BERT competitive performance but also result in slow speed at model inference time. To speed up BERT inference, FastBERT realizes adaptive inference with an acceptable drop in accuracy based on knowledge distillation and the early-exit technique. However, many factors may limit the performance of FastBERT, such as the teacher classifier that is not knowledgeable enough, the batch size shrinkage and the redundant computation of student classifiers. To overcome these limitations, we propose a new BERT inference method with GPU-Efficient Exit Prediction (GEEP). GEEP leverages the shared exit loss to simplify the training process of FastBERT from two steps into only one step and makes the teacher classifier more knowledgeable by feeding diverse Transformer outputs to the teacher classifier. In addition, the exit layer prediction technique is proposed to utilize a GPU hash table to handle the token-level exit layer distribution and to sort test samples by predicted exit layers. In this way, GEEP can avoid batch size shrinkage and redundant computation of student classifiers. Experimental results on twelve public English and Chinese NLP datasets prove the effectiveness of the proposed approach. The source codes of GEEP will be released to the public upon paper acceptance.