检索结果-内蒙古大学图书馆

Proceedings of the 51st International Conference on Parallel Processing

作者： Zhengbo Chen Qi Yu Fang Zheng Feng Guo Zuoning Chen Information Engineering University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Chinese Academy of Engineering China

ISBN: (纸本)9781450397339

Ever-growing CNN size incurs a significant amount of redundancy in model parameters, which in turn, puts considerable burden on hardware. Unstructured pruning is widely used to reduce model sparsity. While, the irregularity introduced by unstructured pruning makes it difficult to accelerate sparse CNNs on systolic array. To address this issue, a variety of accelerators have been proposed. SIGMA, the state-of-the-art sparse GEMM accelerator, achieves significant speedup over systolic array. However, SIGMA suffers from two disadvantages: 1) it only supports one-side sparsity, leaving potential for further performance gains; 2) SIGMA improves utilization of large-sized systolic arrays at the cost of extra overhead. In this paper, we propose DSSA, a dual-side sparse systolic array, to accelerate CNN training. DSSA bases its designs on a small-sized systolic array, which naturally achieves higher cell utilization without additional overhead. To facilitate dual-side sparsity processing, DSSA utilizes a cross-cycle reduction module to accumulate partial sum that belongs to the same column but being processed in different cycles. A comprehensive design space exploration is performed to seek the local optimal configurations for DSSA. We implement the logic design of DSSA using Verilog in RTL and evaluate its performance using a C++-based cycle-accurate performance simulator we built. Experimental results show that DSSA delivers, on average, a speedup of 2.13x and 13.81x over SIGMA and a basic systolic array with the same number of cells. Compared to SIGMA, DSSA incurs 16.59% area overhead and 25.49% power overhead when sparse filter is excluded, as SIGMA did.

关键词： Convolutional Neural Network Hardware Accelerator Sparsity Processing Systolic Array Unstructured Pruning

来源：评论

学校读者我要写书评

暂无评论

Utilization-Aware Data Variable Allocation on NVM- Based SPM in Real-Time Embedded Systems

引用

Journal of Electronic Science and Technology 2021年第2期19卷 163-172页

作者： Jin-Yu Zhan Yi-Xin Li Wei Jiang Jun-Huan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054 State Key Lab of Mathematical Engineering and Advanced Computing Wuxi 214000

With the development of the nonvolatile memory(NVM),using NVM in the design of the cache and scratchpad memory(SPM)has been *** paper presents a data variable allocation(DVA)algorithm based on the genetic algorithm for NVM-based SPM to prolong the *** lifetime can be formulated indirectly as the write counts on each SPM *** the differences between global variables and stack variables,our optimization model has three *** constraints of the central processing unit(CPU)utilization and size are used for all variables,while no-overlay constraint is only used for stack *** satisfy the constraints of the optimization model,we use the greedy strategy to generate the initial population which can determine whether data variables are allocated to SPM and distribute them evenly on SPM ***,we use the Mälardalen worst case executive time(WCET)benchmark to evaluate our *** experimental results show that the DVA algorithm can not only obtain close-to-optimal solutions,but also prolong the lifetime by 9.17% on average compared with SRAM-based SPM.

关键词： Data variables allocation genetic algorithm nonvolatile momory(NVM) scratchpad memory(SPM)

来源：评论

学校读者我要写书评

暂无评论

Software Vulnerability Mining Techniques Based on Data Fusion and Reverse engineering

引用

Wireless Communications and Mobile computing 2022年第0期2022卷

作者： Liu, Tieming State Key Laboratory of Mathematical Engineering and Advanced Computing Henan Zhengzhou450001 China

Software vulnerability mining is an important component of network attack and defense technology. To address the problems of high leakage rate and false positive rate of existing static analysis methods, this paper proposes a static analysis vulnerability detection technique based on data fusion for source code. By parsing the analysis results of different detection methods and fusing the data, the technique can effectively reduce the false positive rate and the false positive rate. A prototype of a scalable source code static analysis tool is designed and implemented, which can be automatically optimized by user feedback. Finally, an example is given to demonstrate how to uncover buffer overflow software vulnerabilities in the helpctr program based on reverse engineering techniques. The experimental results show that the false positive and false negative rates are significantly reduced compared to individual vulnerability detection methods. © 2022 Tieming Liu.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Gravitational wave search by time-scale-recursive denoising and matched filtering

引用

Science China(Physics,Mechanics & Astronomy) 2024年第12期67卷 166-182页

作者： Cunliang Ma Chenyang Ma Zhoujian Cao Mingzhen Jia School of Information Engineering Jiangxi University of Science and TechnologyGanzhou341000China Institute for Frontiers in Astronomy and Astrophysics Beijing Normal UniversityBeijing102206China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou310024China Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Ganzhou341000China

In our previous work [Physical Review D,2024,109(4):043009],we introduced MSNRnet,a framework integrating deep learning and matched filtering methods for gravitational wave(GW) *** with end-to-end classification methods,MSNRnet is physically *** denoising models and astrophysical discrimination models corresponding to different parameter space were operated independently for the template prediction and *** the MSNRnet has a lot of computational *** this study,we propose a new framework for template prediction,which significantly improves our previous *** new framework consists of the recursive application of denoising models and waveform classification models,which solve the problem of computational *** waveform classification network categorizes the denoised output based on the signal's time *** enhance the denoising performance for long-time-scale data,we upgrade the denoising model by incorporating Transformer and ResNet ***,we introduce a novel training approach that allows for the simultaneous training of the denoising network and waveform classification network,eliminating the need for manual annotation of the waveform dataset required in our previous ***-data analysis results demonstrate that our new method decreases the false alarm rate by approximately 25%,boosts the detection rate by roughly 5%,and slashes the computational cost by around 90%.The new method holds potential for future application in online GW data processing.

关键词： gravitational wave matched filtering deep learning

来源：评论

学校读者我要写书评

暂无评论

Cube Attacks Against Trivium, Kreyvium and ACORN with Practical Complexity 20th

Cube Attacks Against Trivium, Kreyvium and ACORN with Prac...

引用

20th International Conference on Information Security and Cryptology, Inscrypt 2024

作者： Chen, Yanqi Li, Ting Sun, Yao Key Laboratory of Cyberspace Security Defense Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China

ISBN: (纸本)9789819647330

The cube attack is a powerful cryptanalysis technique used against stream ciphers. It enables the retrieval of secret key information by computing the values of superpolys, with unknown secret key bits as variables. A practical key-recovery attack seeks to recover all key bits within a reasonable time complexity. The complexity of such attacks typically involves two main components: (1) the complexity of calculating the superpoly values under the real key, which depends on the size of the mother cube, and (2) the complexity of solving the superpoly system, guess-and-determine techniques are often used to solve the system especially when superpolys are nonlinear. In this paper, we improve the best-known practical key-recovery attack on Trivium by enhancing the techniques used in these two areas. First, we introduce a heuristic method to search for good mother cubes, enabling many balanced superpolys to recover. Second, we propose an efficient MILP-based model to search for a minimal number of guessed variables to solve the balanced superpoly systems, thus reducing the complexity of solving the system. With these advancements, we achieve key-recovery attacks on the 830- and 832-round Trivium within practical time complexity, surpassing the previous best result of 825 rounds. Additionally, we applied our new model to attack ACORN with 128-bit keys, achieving practical key-recovery attacks on the 507- and 611-round versions, compared to the previous highest of 477 rounds. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Sample Analysis Based on Dynamic Binary Platform

Vulnerability Sample Analysis Based on Dynamic Binary Platfo...

引用

2021 International Conference on Aviation Safety and Information Technology, ICASIT 2021

作者： Bu, Wenjuan Kang, Fei Zhao, Yuntian Xu, Jianbo State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Henan Zhengzhou450000 China

ISBN: (纸本)9781450390422

Based on the existing vulnerability exploitation detection technology, this paper analyzes the buffer overflow vulnerability exploitation process, and detects vulnerability triggering, protection mechanism bypassing and shellcode execution by dynamic binary instrumentation (DBI) monitoring program execution process;According to the analysis of vulnerability sample shellcode behavior, the method of recording instruction information and key API function information is designed based on instrumentation API function;A prototype platform of vulnerability sample transplantation and utilization based on dynamic binary is designed and implemented, and test analysis of 40 typical vulnerability samples is carried out to verify the effectiveness and feasibility of the system. © 2021 ACM.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Open Set Recognition for Encrypted Traffic using Intra-class Partition and Boundary Sample Generation 5

Open Set Recognition for Encrypted Traffic using Intra-class...

引用

5th IEEE advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

作者： Li, Xue Fei, Jinlong Qi, Zan Lv, Zhuo Jiang, Heng PLA Information Engineering University State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China PLA Information Engineering University National Digital Switching System Engineering Technological Research Center Zhengzhou China

ISBN: (纸本)9781665479677

Existing deep learning-based encrypted traffic recognition methods can achieve high precision identification performance while protecting user privacy, but almost all of them focus on closed sets, in which training data and test data come from the same label space. However, the real network environment is open, and it is necessary for traffic identification systems to deal with previously unseen categories. To classify known categories at a fine granularity and identify unknown ones, we propose a novel open-set recognition method for encrypted traffic. The decision boundary sample generation method based on constrained Generative Adversarial Networks is presented to generate samples from low-density regions in the known data space. Furthermore, an end-to-end open-set classifier is built using the accurate and diverse simulative samples of unknown classes through intra-class partition and boundary sample generation. Finally, the effectiveness of the proposed method is validated through numerical experiments. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain Privacy Protection Based on Post Quantum Threshold Algorithm

引用

Computers, Materials & Continua 2023年第7期76卷 957-973页

作者： Faguo Wu Bo Zhou Jie Jiang Tianyu Lei Jiale Song Institute of Artificial Intelligence Beihang UniversityBeijing100191China Zhongguancun Laboratory Beijing100094China Key Laboratory of Mathematics Informatics and Behavioral Semantics(LMIB)Beihang UniversityBeijing100191China Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang UniversityBeijing100191China LMIB and School of Mathematical Sciences Beihang UniversityBeijing100191China

With the rapid increase in demand for data trustworthiness and data security,distributed data storage technology represented by blockchain has received unprecedented *** technologies have been suggested for various uses because of their remarkable ability to offer decentralization,high autonomy,full process traceability,and tamper *** enables the exchange of information and value in an untrusted *** has been a significant increase in attention to the confidentiality and privacy preservation of blockchain *** data privacy is a critical concern in cryptography,and one of the most important protocols used to achieve this is the secret-sharing *** dividing the secret into shares and distributing them among multiple parties,no one can access the secret without the cooperation of the other ***,Attackers with quantum computers in the future can execute Grover’s and Shor’s algorithms on quantum computers that can break or reduce the currently widely used ***,centralized management of keys increases the risk of key *** paper proposed a post-quantum threshold algo-rithm to reduce the risk of data privacy leakage in blockchain *** algorithm uses distributed key management technology to reduce the risk of individual node private key leakage and provide post-quantum *** proposed privacy-preserving cryptographic algorithm provides a post-quantum threshold architecture for managing data,which involves defining users and interaction processes within the *** paper applies a linear secret-sharing solution to partition the private key of the Number Theory Research Unit(NTRU)algorithm into n *** constructs a t–n threshold that allows recovery of the plaintext only when more than t nodes participate in *** characteristic of a threshold makes the scheme resistant to collusion attacks from members whose combined credibility is less than the

关键词： Blockchain post-quantum cryptography threshold cryptography privacy protection

来源：评论

学校读者我要写书评

暂无评论

MFN: Explainable DNA triple helixes Stabilized Design based on mCGR and flow network

MFN: Explainable DNA triple helixes Stabilized Design based ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wen, Xiaoru Sun, Lijun Xie, Lei Zheng, Yanfen Cao, Ben Wang, Bin Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9798350386226

DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect their wide application in gene therapy. Therefore, in this paper, we propose an antiparallel DNA triple helixes design method-MFN based on matrix chaotic game representation (mCGR) and flow network. Leveraging the structural characteristics of DNA sequences, this method employs the mCGR algorithm to construct an initial matrix, generating a set of DNA sequences that conform to foundational constraints. Then, these sequences are mapped as stream network nodes to screen crosstalk structures by path search, and the whole process is observable and interpretable. Experimental results show that MFN significantly improves the design efficiency of triple helix structure and reduces crosstalk phenomenon. Wet experiments further verify the effectiveness of the method. In summary, MFN achieves an efficient and high-quality design of DNA triple helixes and provides a new idea for targeted gene therapy. © 2024 IEEE.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Convergence of Physics-Informed Neural Networks Applied to Linear Second-Order Elliptic Interface Problems

引用

Communications in Computational Physics 2023年第2期33卷 596-627页

作者： Sidi Wu Aiqing Zhu Yifa Tang Benzhuo Lu State Key Laboratory of Scientific and Engineering Computing National Center for Mathematics and Interdisciplinary SciencesAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China.

With the remarkable empirical success of neural networks across diverse scientific disciplines,rigorous error and convergence analysis are also being developed and ***,there has been little theoretical work focusing on neural networks in solving interface *** this paper,we perform a convergence analysis of physics-informed neural networks(PINNs)for solving second-order elliptic interface ***,we consider PINNs with domain decomposition technologies and introduce gradient-enhanced strategies on the interfaces to deal with boundary and interface jump *** is shown that the neural network sequence obtained by minimizing a Lipschitz regularized loss function converges to the unique solution to the interface problem in H2 as the number of samples *** experiments are provided to demonstrate our theoretical analysis.

关键词： Elliptic interface problems generalization errors convergence analysis neural networks.

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：