检索结果-内蒙古大学图书馆

2021 International Symposium on Computer Technology and Information Science, ISCTIS 2021

作者： Cheng, Sipeng Sha, Zihan Yu, Pu Bu, Wenjuan Huo, Guovu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665414418

To address the characteristics of traditional obfuscation methods such as single approach and obvious features, a Parent-based Powershell Script Fusion Technology is proposed based on code fusion. This technology uses the target script to undergo slice encryption processing, and in-depth fusion with the parent script in the execution logic and execution flow, and uses the parent script to conceal the behavior characteristics of the target script. A number of Powershell scripts commonly used for infiltration are selected as the test set to test the proposed technique. The test results show that the proposed technique can reduce the detection rate of the antivirus engine for the target script and has a greater advantage in anti-static analysis. © 2021 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Identify IoT Devices through Web Interface Characteristics 6

Identify IoT Devices through Web Interface Characteristics

引用

6th IEEE International Conference on Computer and Communication Systems, ICCCS 2021

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

ISBN: (纸本)9780738126043

With the continuous expansion of the business scale of the Internet of Things, the concept of the Internet of Everything has been deeply rooted in the hearts of the people. At the same time, various security issues have been exposed, which has greatly affected the trust of enterprises and users. Discovering and identifying IoT devices as an important part of IoT security should be taken seriously. In this paper, we propose a new method for classifying devices on the Internet of Things, which uses the data characteristics of the main page of the device's web interface to classify the vendor name, even the product name and other information of the device. We randomly selected IP address ranges on the Internet for scanning, and obtained a training set containing 80, 000 entries and covering more than 1, 000 devices from 74 vendors. Using the random forest algorithm and proceeding 10-fold cross-validation, our method classified IoT devices with an accuracy rate of over 97.5%. © 2021 IEEE.

关键词： Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

Integrating KNN and Gradient Boosting Decision Tree for Recommendation 5

Integrating KNN and Gradient Boosting Decision Tree for Reco...

引用

5th IEEE advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Du, Qiming Li, Nan Yang, Shudan Sun, Daozhu Liu, Wenfu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781728180281

As an efficient information filtering tool, the recommendation system can help users obtain valuable information quickly and efficiently while effectively alleviating the information load problem. However, the classic collaborative filtering algorithm has data sparsity problems in practical applications, which affects the accuracy of recommendation. To solve this problem, this paper took movie recommendation as the research object and proposed a hybrid recommendation algorithm named K-GBDT which combined KNN and gradient boosting decision tree. Firstly, it used KNN to obtain the similar information of the target user and item for preliminary prediction. At the same time, it mined users' basic information features and potential features of users and items from the original data. Then, it tried to adopt XGBoost, LightGBM and CatBoost algorithm which were proposed base the idea of gradient boosting decision tree to build regression model. Finally, the target user's rating for the movie was predicted with the trained model, and the recommendation list was generated based on the predicted results. Compared with some classic recommendation algorithms such as NMF, Slope One, Co-Clustering and etc. Based on MovieLens datasets, results show that the mean absolute error and root mean square error of this algorithm are both low, and its recommendation accuracy is higher. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Code Obfuscation Based on Inline Split of Control Flow Graph

Code Obfuscation Based on Inline Split of Control Flow Graph

引用

2021 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2021

作者： Li, Yang Sha, Zihan Xiong, Xiaobing Zhao, Yuntian State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665418676

Control flow graph is an important concept in the field of program analysis, which represents the source program in the form of graph. On the control flow graph, we can easily analyze the predecessor and successor relationship among basic blocks. This paper we inline the functions in the original program and outline the inlined program randomly to form outline functions. Therefore, we convert the intra-procedure basic block jump to an inter-procedure function call, which hides the basic block jump relationship in the process and obfuscates the function boundaries. In order to further increase the intensity of obfuscation, a bogus function similar to the outline function is added, and the bogus control flow is added in combination with opaque predicates simultaneously. Based on the above work, this paper proposes an obfuscation algorithm which converges and splits the program control flow graph. We utilize the commonly used cryptographic hash algorithm as the test set, and verify the feasibility and effectiveness of the obfuscation algorithm. © 2021 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Inter-domain Link Inference with Confidence Using Naïve Bayes Classifier 2021

Inter-domain Link Inference with Confidence Using Naïve Bay...

引用

2021 13th International Conference on Machine Learning and computing, ICMLC 2021

作者： Zhao, Yi Liu, Yan Guo, XiaoYu Sui, ZhongHang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781450389310

Inter-domain link inference is not only important for network security and fault diagnosis, but also helps to conduct research on inter-domain congestion detection and network resilience assessment. Current researches on this issue lack confidence analysis of the inferred results. In this paper, the IP link types (i.e., intra-domain link and inter-domain link) are considered as the latent variable in probability model, while the parameters are probabilities of different link types with particular features. The expectation maximization algorithm is applied to estimate parameters of the model. In each iteration of EM algorithm, Naïve Bayes is used for classification. The final result is determined according to the probability, and the probability is the confidence of the result. The experimental results show that our method can achieve better precision and recall on the validation set than two existing general methods. © 2021 ACM.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Semantic Understanding of Source and Binary Code based on Natural Language Processing 4

Semantic Understanding of Source and Binary Code based on Na...

引用

4th IEEE advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2021

作者： Zhang, Zhongtang Liu, Shengli Yang, Qichao Guo, Shichen State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781728185347

With the development of open source projects, a large number of open source codes will be reused in binary software, and bugs in source codes will also be introduced into binary codes. In order to detect the reused open source codes in binary codes, it is sometimes necessary to compare and analyze the similarity between source codes and binary codes. One of the main challenge is that the compilation process can generate different binary code representations for the same source code, such as different compiler versions, compilation optimization options and target architectures, which greatly increases the difficulty of semantic similarity detection between source code and binary code. In order to solve the influence of the compilation process on the comparison of semantic similarity of codes, this paper transforms the source code and binary code into LLVM intermediate representation (LLVM IR), which is a universal intermediate representation independent of source code and binary code. We carry out semantic feature extraction and embedding training on LLVM IR based on natural language processing model. Experimental results show that LLVM IR eliminates the influence of compilation on the syntax differences between source code and binary code, and the semantic features of code are well represented and preserved. © 2021 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Dynamic Instrumentation Framework Based on Entity Equipment 6

Dynamic Instrumentation Framework Based on Entity Equipment

引用

6th IEEE International Conference on Computer and Communication Systems, ICCCS 2021

作者： Jiangtao, Zhao Dong, Weiyu Zhang, Haotian Lin, Jian State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9780738126043

Dynamic binary analysis is an important way of program analysis. Most of the existing dynamic analysis tools are based on dynamic binary instrumentation platforms. The existing gdb tool, which is often used for debugging of embedded devices, has low performance on dynamic instrumentation. This paper implements basic block-level instrumentation based on dynamic binary rewriting technology and provides a simple and flexible application programming interface. Through the evaluation, the local instrumentation efficiency of this system is mostly better than the Pin platform, and the remote instrumentation efficiency is about 28.7 times that of the gdb+gdbserver platform. The instrumentation performance has been greatly improved. © 2021 IEEE.

关键词： Efficiency

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

Research on security assessment based on big data and multi-entity profile 5

Research on security assessment based on big data and multi-...

引用

5th IEEE advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Liu, Wenfu Pang, Jianmin Yang, Shudan Li, Nan Du, Qiming Sun, Daozhu Liu, Fudong State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

Security assessment is one of the important problems, especially in the fields of military training, transportation and network management. The security "related parties"(entities in this paper) have internal relations in the three fields. It is of great significance of constructing the attributes of these entities or even designing a unified security assessment method. Security assessment in these areas has been studied and explored for a long time. However, the research is relatively scattered and unilateral. It is no unified and reusable method from data collection to security assessment. Based on the advantages of big data technology in the storage and analysis of massive data, the paper proposed a security risk element acquisition method from data collection and preprocessing, storage and mining to attribute extraction and aggregation. In addition, drawing on the idea of user portraits in other fields, constructed personnel entities, equipment entities and "other"entity labels related to security risks. Finally, a security risk assessment process based on these entities is designed. © 2021 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Advancing Quantization Steps Estimation: A Two-Stream Network Approach for Enhancing Robustness 24

Advancing Quantization Steps Estimation: A Two-Stream Networ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Cheng, Xin Wang, Hao Wang, Jinwei Luo, Xiangyang Ma, Bin Nanjing University of Information Science and Technology Nanjing China Huaiyin Institute of Technology Huai'an China Nankai University Tianjin China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Qilu University of Technology Jinan China

ISBN: (纸本)9798400706868

In Joint Photographic Experts Group (JPEG) image steganalysis and forensics, the quantization step can reveal the history of image operations. Several methods for estimating the quantization step have been proposed by researchers. However, existing algorithms fail to account for robustness, which limits the application of these algorithms. To solve the above problems, we propose a two-stream network structure based on Swin Transformer. The spatial domain features of JPEG images exhibit strong robustness but low accuracy. Conversely, frequency domain features demonstrate high accuracy but weak robustness. Therefore, we design a two-stream network with the multi-scale feature of Swin Transformer to extract spatial domain features with high robustness and frequency domain features with high accuracy, respectively. Furthermore, to adaptively fuse features in both the frequency domain and spatial domain,we design a Spatial-frequency Information Dynamic Fusion (SIDF) module to dynamically allocate weights. Finally, we modify the network from a regression model to a classification model to speed up convergence and improve the accuracy of the algorithm. The experiment results show that the accuracy of the proposed method is higher than 98% on clean images. Meanwhile, in robust environments, the algorithm proposed maintains an average accuracy of over 81%. © 2024 ACM.

关键词： Frequency domain analysis

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：