检索结果-内蒙古大学图书馆

7th International Conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Yuan, Huijie Wang, Yunchao Zong, Guoxiao Lv, Zhuo State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China State Grid Electric Power Research Institute Zhengzhou China

ISBN: (纸本)9781665478571

The reuse of public component libraries has contributed to the field of computer science because of its low implementation time and high production efficiency. However, the vulnerabilities in libraries can be more serious than those in real-world software because they can affect various software which uses these libraries. Therefore, the technologies of vulnerability mining of public component libraries have received extensive attention, such as fuzzing. But the number of crashes generated by fuzzing is huge, and only an exceedingly small number of public component library vulnerabilities are exploitable in real-world software. To solve this problem, we use taint analysis techniques to analyze the exploitability of library vulnerabilities in real-world software. We first use Pin binary instrumentation technology to instrument the consumer program, analyze the process of calling the library in the consumer program through the taint analysis, and convert the extracted execution path and parameter information into an adjacency matrix. Then we analyze the execution path and crash scene of the crash file, convert the exploitability analysis into path reachability analysis, and determine whether the crash can reach the vulnerable pointer of the software through reachability. Finally, we divide the library vulnerabilities into three levels: directly exploitable, indirectly exploitable, and unexploitable. We design and implement a prototype tool, LibExp-T, to analyze nine public component libraries and four real-world software containing multiple attack surfaces such as images, audio, video, fonts, etc. And we compare them with automatic exploit generation tools CRAX and REX. The results show that LibExp-T can effectively verify the exploitability of component library vulnerabilities in real-world software with low overhead. © 2022 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

A Firmware Vulnerability Detection Method Based on Feature Filtering 21

A Firmware Vulnerability Detection Method Based on Feature F...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud computing, 16th IEEE International Conference on Social computing and Networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Xia, Bing Tang, Chongjun Liu, Wenbo Chu, Shihao Dong, Yu ZhongYuan University of Technology Key Laboratory of Mathematical Engineering and Advanced Computing Dept Zhengzhou China ZhongYuan University of Technology Henan Key Laboratory on Public Opinion Intelligent Analysis Dept Zhengzhou China ZhongYuan University of Technology Dept Zhengzhou China

ISBN: (纸本)9798350329223

Open source code reuse and code cross-platform deployment accelerate the spread of software vulnerabilities, and pose challenges for accurate detection of cross-platform vulnerabilities. The binary vulnerability similarity detection method based on machine learning lacks a fine-grained vulnerability similarity feature filtering mechanism, and cannot solve cross-function vulnerabilities triggered by data dependencies, resulting in a high vulnerability false positive rate in existing solutions, which limits practical applications. Software code vulnerabilities are usually caused by function key statements. Therefore, based on binary function decompilation, we identify the key statement that causes the vulnerability, analyze the cross-function data dependency of the key statements, extract the code similarity features and code vulnerability features of the key statements, and propose a feature filtering-based Binary vulnerability detection method SimFilter. SimFilter calculates the similarity of key statements by comparing the characteristics of function key statements, and infers the similarity of binary function vulnerabilities based on the similarity of key statements. The experimental results show that the vulnerability semantic features extracted by SimFilter are highly interpretable, and the accuracy rate is increased by 10.8% compared with other models. At the same time, we analyzed and evaluated the impact of different similarity features on the accuracy of SimFilter, and gave the best empirical value of the SimFilter model in firmware vulnerability detection. © 2023 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

SoK: A Survey on Redundant Execution Technology

SoK: A Survey on Redundant Execution Technology

引用

2021 International Conference on advanced computing and Endogenous Security, ICACES 2021

作者： Liu, Zijing Zhang, Zheng Xi, Ruicheng Zhu, Pengzhe Ma, Bolin State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665424493

Redundant execution technology is one of the effective ways to improve the safety and reliability of computer systems. By rationally configuring redundant resources, adding components with the same function, using the determined redundant execution logic to coordinate and efficiently execute synchronously can effectively ensure high availability of the machine and system. Fault-tolerant is based on redundant execution, which is the primary method of dealing with system hardware failures. Recently, multi-threading redundancy has realized the continuous development of fault-tolerant technology, which makes the processing granularity of the system tolerate random failure factors gradually reduced. At the same time, intrusion tolerant technology has also been continuously developed with the emergence of multi-variant execution technology. It mainly uses the idea of dynamic heterogeneous redundancy to construct a set of variants with equivalent functions and different structures to complete the detection and processing of threats outside the system. We summarize the critical technologies of redundant execution to achieve fault tolerance and intrusion tolerance in recent years, sorts out the role of redundant execution in the development process from fault tolerance technology to intrusion tolerance technology, classify redundant execution technologies at different levels, finally point out the development prospects of redundant execution technology in multiple application fields and future technical research directions. © 2022 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Binary Network Protocol Segmentation Based on Probabilistic Inference

SSRN

引用

SSRN 2023年

作者： Guo, Maohua Fei, Jinlong Zhu, Yuefei State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450000 China

Protocol Reverse engineering (PRE) is of great practical importance in Internet security-related fields such as intrusion detection, vulnerability mining, and protocol fuzzing. For unknown binary protocols having fixed-length fields, and the accurate identification of field boundaries has a great impact on the subsequent analysis and final performance. Hence, this paper proposes a new protocol segmentation method based on Information-theoretic statistical analysis for binary protocols by formulating the field segmentation of unsupervised binary protocols as a probabilistic inference problem and modeling its uncertainty. Specifically, we design four related constructions between entropy changes and protocol field segmentation, introduce random variables, and construct joint probability distributions with traffic sample observations. Probabilistic inference is then performed to identify the possible protocol segmentation points. Extensive trials on nine common public and industrial control protocols show that the proposed method yields higher-quality protocol segmentation results. © 2023, The Authors. All rights reserved.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

KVM PT Based Coverage Feedback Fuzzing for Network key Devices 2

KVM PT Based Coverage Feedback Fuzzing for Network Key Devic...

引用

2nd International Conference on Computer engineering and Application, ICCEA 2021

作者： Zhiqiang, Lin Jianshan, Peng Yechuan, Bi Xiaowei, Li State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665426169

With the advent of the network era, network security has attracted more and more attention. As the key node in the network, network key devices play an important role in protecting the internal network and ensuring the network security. For the vulnerability of network key devices, security analysis has become an important concern of security personnel. Fuzzing is an automatic and effective vulnerability mining technology. In this paper, we propose the first coverage feedback fuzzy testing framework based on KVM PT technology for network key devices, aiming to solve the feasibility of applying fuzzy tools in network critical devices. At the same time, a fuzzy test agent technology based on firmware modification is proposed to help speed up the call of testcases. We evaluated the framework on Cisco ASA firewall, and trigger CVE-2018-0101, which proves the effectiveness of the framework. © 2021 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Zero WFuzzer: Target-Oriented Fuzzing for Web Interface of Embedded Devices 4

Zero WFuzzer: Target-Oriented Fuzzing for Web Interface of E...

引用

4th IEEE International Conference on Computer and Communication engineering Technology, CCET 2021

作者： Zheng, Yan Dong, Weiyu Cheng, Hui State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665438902

With the popularization of embedded devices, security issues continue to occur. The existing automated security testing methods for embedded devices are mainly carried out from two aspects: the Web interface of the device or the firmware binary file. This paper proposes a testing framework ZeroWFuzzer that combines the Web interface of embedded devices with firmware binary, which automatically generates test cases through the Web interface, and uses binary instrumentation to guide the fuzzing test. Experiments in embedded devices have found that ZeroWFuzzer has higher efficiency and quantity of triggering vulnerabilities than the protocol fuzzing tool Boofuzz and the Web security testing tool Xray. © 2021 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification

arXiv

引用

arXiv 2024年

作者： Liu, Chun Zhang, Hongguang Zhao, Kainan Ju, Xinghai Yang, Lin Systems Engineering Institute AMS Beijing China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text classification. However, most of these methods are based on heuristic Chain-of-Thought (CoT), and tend to be more complex but less efficient. In this paper, we rethink the LLM-based text classification methodology, propose a simple and effective transfer learning strategy, namely LLMEmbed, to address this classical but challenging task. To illustrate, we first study how to properly extract and fuse the text embeddings via various lightweight LLMs at different network depths to improve their robustness and discrimination, then adapt such embeddings to train the classifier. We perform extensive experiments on publicly available datasets, and the results show that LLMEmbed achieves strong performance while enjoys low training overhead using lightweight LLM backbones compared to recent methods based on larger LLMs, i.e. GPT-3, and sophisticated prompt-based strategies. Our LLMEmbed achieves adequate accuracy on publicly available benchmarks without any fine-tuning while merely use 4% model parameters, 1.8% electricity consumption and 1.5% runtime compared to its counterparts. Code is available at: https://***/ChunLiu-cs/LLMEmbed-ACL2024. © 2024, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Non-Local and Fully Connected Tensor Network Decomposition for Remote Sensing Image Denoising

引用

高等学校计算数学学报（英文版） 2024年第2期17卷 379-403页

作者： Zhihui Tu Shunda Chen Jian Lu Lin Li Qingtang Jiang Shenzhen Key Laboratory of Advanced Machine Learning and Applications School of Mathematical SciencesShenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of Advanced Machine Learning and Applications School of Mathematical SciencesShenzhen UniversityShenzhen 518060China National Center for Applied Mathematics Shenzhen(NCAMS) Shenzhen 518055China Pazhou Lab Guangzhou 510320China School of Electronic Engineering Xidian UniversityXi'an 710071China Department of Mathematics and Statistics University of Missouri-St.LouisSt.LouisMO 63121USA

Remote sensing images(RSIs)encompass abundant spatial and spec-tral/temporal information,finding wide applications in various ***,during image acquisition and transmission,RSI often encounter noise interference,which adversely affects the accuracy of subsequent *** address this is-sue,this paper proposes a novel non-local fully connected tensor network(NLFCTN)decomposition algorithm for denoising RSI,aiming to fully exploit their global cor-relation and non-local self-similarity(NSS)***,as a recently de-veloped tensor decomposition technique,exhibits remarkable capability in captur-ing global correlations and minimizing information *** addition,we introduce an efficient algorithm based on proximal alternating minimization(PAM)to effi-ciently solve the model and prove the *** effectiveness of the pro-posed method is validated through denoising experiments on both simulated and real RSI data,employing objective evaluation metrics and subjective visual *** results of the experiment show that the proposed method outperforms other RSI denoising techniques in terms of denoising performance.

关键词： Remote sensing images denoising tensor decomposition non-local self-similarity

来源：评论

学校读者我要写书评

暂无评论

Bi-population genetic algorithm-based attack path discovery research in large-scale networks 4

Bi-population genetic algorithm-based attack path discovery ...

引用

4th World Conference on computing and Communication Technologies, WCCCT 2021

作者： Tairan, Hu Wenlong, Gao Tianyang, Zhou Yichao, Zang National Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9780738144986

with the growth of network scale, present researches on the attack path discovery often encounter the problem of search space explosion that results in fails. To tackle the problem of attack path discovery for large-scale networks, this paper proposes a bi-population genetic algorithm for the attack path discovery in large-scale networks. Firstly, this paper represents the connective relationship between hosts as vectors and uses the Balanced Iterative Reducing and Clustering Using Hierarchies (Birch) algorithm to realize network decomposition. Then, the attack path discovery problem is encoded based on the decomposition result, and the bi-population mechanism is introduced to find the attack path. The experiment result shows that our algorithm performs better than Metric-FF and SGA in optimization and efficiency. © 2021 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Approach with Clustering-Based Under-sampling for Imbalanced Classification 2

An Ensemble Approach with Clustering-Based Under-sampling fo...

引用

2nd International Conference on Artificial Intelligence and Education, ICAIE 2021

作者： Ren, Huajuan Ren, Shuai Yan, Lin Wang, Ruimin Jing, Jing Shi, Jiaqi State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665424929

Class imbalance widely occurs in many real-world applications, which affects the recognition of important class to a certain extent. Ensemble methods that combined resampling are effective to alleviate the class imbalance problems. This paper presents a new ensemble approach with clustering-based under-sampling, called CNBoost, for learning from imbalanced data. This algorithm is based on the combination of Centers NN and boosting procedure. Centers NN, as an under-sampling utilizing the nearest neighbors of cluster centers, is used to provide a new training subset in each iteration of boosting, which makes the base learner learn the overall data distribution in each iteration of boosting. We compared the performance of the proposed algorithm with 3 popular ensemble methods. Out of 10 datasets and 3 measurements, CNBoost performs equally well or better than the other 3 methods in 25/30 categories. In addition, we discussed the effect of the base learner used in boosting on the performance of these algorithms. The results show that CNBoost is a promising approach with high classification accuracy and stability for dealing with imbalanced datasets. © 2021 IEEE.

关键词： Iterative methods

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：