Sparse matrix vector multiplication is an important and commonly used computing kernel in scientific computing. Irregular arrangement of non zeros in sparse matrix leads to irregular memory access pattern, which in tu...
详细信息
Sparse matrix vector multiplication is an important and commonly used computing kernel in scientific computing. Irregular arrangement of non zeros in sparse matrix leads to irregular memory access pattern, which in turn affects the running speed. In the past ten years, there have been many optimization methods of sparse matrix vector multiplication based on different ideas and techniques. In this paper, the commonly used performance optimization techniques of sparse matrix vector multiplication in multi/many-core architecture are comprehensively investigated. We classify technical methods according to their common characteristics, and discuss the problems encountered by researchers of various methods. In addition, We provide a typical large sparse matrix set for testing. This paper also provides a theoretical basis for our subsequent sparse matrix calculation in Sunway TaihuLight archiecture.
Sieve algorithm plays an important role in solving the shortest vector problem, which is one of the most representative hard lattice problems. In this paper, we propose an efficient sieve algorithm with evolutionary t...
详细信息
ISBN:
(数字)9781728181417
ISBN:
(纸本)9781728181424
Sieve algorithm plays an important role in solving the shortest vector problem, which is one of the most representative hard lattice problems. In this paper, we propose an efficient sieve algorithm with evolutionary techniques. By combining Gauss Sieve algorithm with global selection, we propose an efficient sieve algorithm. Experimental results show that our algorithm performs better than FPLLL's Gauss Sieve algorithm in solving the shortest vector problem. Furthermore, we explore how mutation behaves in accelerating sieve algorithm.
Vulnerability detection, especially vulnerability automatic detection, have long been an area of active research. Considering that RNN can model dependencies automatically, we propose a recurrent neural network (RNN) ...
详细信息
ISBN:
(纸本)9781450372619
Vulnerability detection, especially vulnerability automatic detection, have long been an area of active research. Considering that RNN can model dependencies automatically, we propose a recurrent neural network (RNN) based method for binary code vulnerability detection. We collected correspond to 4 types of vulnerabilities, including CWE-134, CWE-191, CWE-401 and *** find which RNN is better in vulnerability detection, we evaluated 6 different RNNs, including SRNN, BSRNN, LSTM, BLSTM, GRU and BGRU. The results demonstrated that BSRNN is better than others in vulnerability detection.
HTTPS protocol is utilized to protect personal privacy in network communication by man-in-the-middle attacks. However, after the browser is attacked, this protection mechanism will be destroyed. This paper analyzes th...
详细信息
ISBN:
(数字)9781728181417
ISBN:
(纸本)9781728181424
HTTPS protocol is utilized to protect personal privacy in network communication by man-in-the-middle attacks. However, after the browser is attacked, this protection mechanism will be destroyed. This paper analyzes the vulnerability of https protocol under two scenarios of operating system and network data transmission. Based on the untrusted situation, the possibility of implementing HTTPS protocol injection and page injection on the browser side was analyzed. A traffic monitoring and detection scheme based on dynamic rules is proposed, which can effectively detect whether the browser is injected with malicious code. False positive is less than 10%.
In this paper, we propose a SH2I2 rumor propagation model considering self-learning mechanism and echo chamber situation with Holling type II functional response in homogeneous and heterogeneous networks. Firstly, we ...
详细信息
ISBN:
(数字)9781665422321
ISBN:
(纸本)9781665446662
In this paper, we propose a SH2I2 rumor propagation model considering self-learning mechanism and echo chamber situation with Holling type II functional response in homogeneous and heterogeneous networks. Firstly, we obtain the basic reproduction number through Jacobian Matrix method and calculate the equilibrium points. Secondly, we prove the existence of rumor-prevailing equilibrium point as well as the local and globally stabilities by Routh-Huiwitz judgment and Lyapunov function. Finally, we use theoretical analysis and numerical simulations to investigate the effect of parameters for suppressing the prevalence of rumors.
The world is full of relationships, and graph is the most evident representation for them. With the increasing of data scale, graphs become larger and have encountered a new world of analyzing. What can we learn from ...
详细信息
The research upsurge of recommendation system and deep learning makes the deep learning based recommendation system become an inevitable trend. Through the introduction of the latest research of deep learning based re...
详细信息
ISBN:
(数字)9781728143231
ISBN:
(纸本)9781728143248
The research upsurge of recommendation system and deep learning makes the deep learning based recommendation system become an inevitable trend. Through the introduction of the latest research of deep learning based recommendation, we present the current popular research directions in the recommendation field and provide a comprehensive review of various advanced technologies. Finally, we propose a new viewpoint on the future development of deep learning based recommendation system.
Considering that the deployment of IoT devices is becoming more and more widespread, the security analysis of the firmware of these devices is extremely important. However, a large number of devices now have vulnerabi...
详细信息
ISBN:
(数字)9781728165790
ISBN:
(纸本)9781728165806
Considering that the deployment of IoT devices is becoming more and more widespread, the security analysis of the firmware of these devices is extremely important. However, a large number of devices now have vulnerabilities that can be exploited, allowing attackers to remotely control IoT devices. In this article, we show FIRMNANO, a fuzzing framework for the firmware of IoT devices with microcontrollers as the core. Based on augmented virtual execution, FIRMNANO solves three key problems of microcontrollers firmware emulation: (1) MMIO region access (2) interrupt triggering (3) DMA support. On this basis, it conducts code coverage-based fuzzing testing for firmware. Our evaluation results show that FIRMNANO can execute firmware correctly and can be used for real-world firmware vulnerability mining.
Aiming at the problem of insufficient defense ability of fingerprint detection,the anti-reconnaissance model of host fingerprint based on virtual node is *** model constructs periodically reconfigurable virtual nodes,...
详细信息
Aiming at the problem of insufficient defense ability of fingerprint detection,the anti-reconnaissance model of host fingerprint based on virtual node is *** model constructs periodically reconfigurable virtual nodes,dynamically camouflages the fingerprint information of the host to deceive the detector,and redirect attack traffic targeting virtual nodes to honeypots that can capture and analyze attack ***,as an active defense technology,can effectively improve the model's defense *** paper introduces probabilistic models for the defense model to provide a deeper understanding of the theoretical effect their parameters have for cybersecurity,which quantifies the impact of different parameters on the probability of attack success,such as the number of probes,number of honeypot mapping rules,the virtual node deception rate,the honeypot detection rate and allowable ***,our prototype system using Software Defined Network(SDN) and Data Plane Development Kit(DPDK) verifies the effectiveness of the model against reconnaissance.
Network topology is one of the most important parts in network security situation awareness tasks. Considering that the topology may change due to network intrusion, adjustment of routing policies, etc., the tradition...
详细信息
暂无评论