检索结果-内蒙古大学图书馆

7th International Conference on advanced Algorithms and Control Engineering, ICAACE 2024

作者： Gao, En We, Jinzhao Yang, Guowu University Of Electronic Science And Technology Of China Chengdu611731 China Guilin University Of Aerospace Technology Guilin541004 China University Of Electronic Science And Technology Of China China Advanced Cryptography And System Security Key Laboratory Of Sichuan Province Chengdu611731 China

ISBN: (纸本)9798350361445

Recently, model acceleration techniques have been applied to Vision Transformers (ViTs) to address their high computation costs, particularly in latency-sensitive domains. advanced techniques primarily focus on token sparsification, aiming to reduce the number of tokens in transformer blocks to accelerate inference. However, they often rely on trial-and-error pruning methods to find a balance between predictive accuracy and pruning efficiency, lacking quantitative characterization. To bridge this gap, this paper introduces an algorithm called Attention Standard deviation based Token Sparsification (ASTS). By utilizing the standard deviation of attention map weights as the threshold for pruning, ASTS removes a specific number of tokens with the lowest attention weights. This approach efficiently adjusts the trade-off between predictive accuracy and pruning efficiency, eliminating the need for extensive exploration in a vast hyper-parameter space. Through extensive experiments on various benchmarks, we empirically validate the effectiveness of the proposed pruning method. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Botnet Data Collection Method for Industrial Internet 20

A Botnet Data Collection Method for Industrial Internet

引用

20th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Jian, Shu Bo, Xian Chenli, Wang Jiazhong, Lu Yuanyuan, Huang Shuo, Han School of Cybersecurity Chengdu University of Information Technology Sichuan Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Sichuan Chengdu610225 China Northwestern University Department of Statistics and Data Sciences EvanstonIL60202 United States

ISBN: (纸本)9798350318982

Industrial internet security is related to industrial production operations and national economic security. Network intrusion detection dataset in industrial control environment can effectively train detection models and mitigate network attacks, which is an indispensable component for industrial internet security. In this paper, we propose a data collection method for industrial Internet-oriented botnet by classifying traffic packets according to network traffic features and industrial control identification codes, containing the status of industrial control devices. This method can greatly improve the detection accuracy of the model in the industrial internet. To create a botnet incursion dataset in the industrial control environment, we simultaneously employed the existing industrial control devices to gather both industrial control and botnet network traffic. Finally, we used an AI-based model to detect the botnet. © 2023 IEEE.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

MC-GAN: An Adversarial Sample Defense Algorithm 20

MC-GAN: An Adversarial Sample Defense Algorithm

引用

20th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Chenli, Wang Juyang, W.U. Xing, Yang Junfei, Wang Jian, S.H.U. Jiazhong, L.U. Yuanyuan, Huang Shuo, H.A.N. School of Cybersecurity Chengdu University of Information Technology Sichuan Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Sichuan Chengdu610225 China Northwestern University Department of Statistics and Data Sciences EvanstonIL60202 United States

ISBN: (纸本)9798350318982

The current adversarial sample defense algorithms are plagued by issues such as poor defense effectiveness and high training costs. In order to enhance sample classification accuracy while reducing training costs, we have introduced a novel defense algorithm based on model compression within the framework of Generative Adversarial Networks (GANs). This algorithm integrates GANs with model compression techniques, and the results of testing on public datasets have demonstrated an improved accuracy in defending against adversarial samples along with reduced training costs. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Across Multiple Domains Using Fuzzy Association Rules 24th

Fake News Detection Across Multiple Domains Using Fuzzy Asso...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xu, Xiaofeng Zhang, Weisha Huang, Yuanyuan Lu, Hongyu Lu, Jiazhong School of Cybersecurity Xin Gu Industrial College Chengdu University of Information Technology Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610225 China SUGON Industrial Control and Security Center Chengdu610225 China School of Foreign Languages University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9789819615247

The detection of fake news is not confined to a single domain, and due to domain transfer, the reliance on detection methods specific to a single domain becomes inadequate when dealing with multi-domain issues. When a multi-domain detection occurs, labels from one domain focus exclusively on the news characteristics of that particular domain, ignoring the possibility that part of the news may include functions from more than one domain. To address these challenges, we propose a multi-domain fake news detection model based on fuzzy rules, incorporating a fuzzy mechanism and an optimization module for fuzzy association rules. In this model, we first introduce a fuzzy mechanism that applies fuzzy processing to domains through neural networks, constructing fuzzy domain labels for each news domain. Subsequently, we incorporate fuzzy association rules to extract a broader range of sample features, thereby enhancing detection effectiveness. Experiments conducted on a fake news dataset demonstrate that our model achieves commendable detection performance with a relatively low training cost, reaching an F1 score of over 97.13% for sample detection. This model successfully overcomes the limitations of single-domain detection in fake news identification and improves the precision of feature extraction through fuzzy rules, showing superior performance in handling multi-domain fake news detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： fake news detection fuzzy rules multi-domain social media

来源：评论

学校读者我要写书评

暂无评论

MS-UCON: A Usage Control Model for Meteorological Operational systems

MS-UCON: A Usage Control Model for Meteorological Operationa...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Dan Long Juan Wang Bin Han Ding Chen Lei Shi Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province

With the national Belt and Road strategy in place, meteorological operational systems will face domestic and international dangers, and it is very urgent and important to protect the safety of meteorological equipment and resources. The existing meteorological operational system uses a role-based access control model for permission management, whose permissions do not change during one authorized access, and cannot sense the threat of user behavior to the system in real time, much less adjust user permissions in time, thus failing to cope with the security needs of the weather business system. In this paper, we propose a Meteorological Operational system-oriented Usage Control (MS-UCON) model to address this problem. The model refines the UCON model according to industry characteristics and business needs, and adds a periodic trust assessment module and a collection of trust value assessment factors to monitor user behavior in real time, perform periodic trust assessment on user behavior, sense user risky behavior in time, dynamically update user trust value attributes, and dynamically adjust permissions. Finally, the security of the MS-UCON model is proved based on state machine theory. The results show that the MS-UCON model can solve the problem that user privileges cannot be dynamically adjusted in meteorological operational systems, and also meet the security requirements of meteorological operational systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Summarizing Videos using the Uniqueness of Video Frames that Mask Adjacent Frame Information

Summarizing Videos using the Uniqueness of Video Frames that...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Yongxin Huang Yimin Zhou Zuli Wang Ding Chen Lei Shi Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province

Video summarization can help people retrieve videos quickly. Existing unsupervised video summarization models make insufficient use of video frame uniqueness in the self-attention mechanism and have redundancy in the computation of uniqueness. In this paper, we rethink the relationship between attentive uniqueness and diversity of video frames, improve the calculation method of video frame uniqueness by masking adjacent frame information in the model framework based on a self-attention mechanism, and simplify the concentrated attention mechanism with it. In addition, we propose a new loss function called Deviation loss, which uses the uniqueness of video frames to calculate and helps train video summarization models to obtain diverse representations. The experimental results show that the proposed method outperforms other state-of-the-art unsupervised summarization approaches on the SumMe dataset, and also demonstrates competitiveness on the TVSum dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Semantic-Constrained Adversarial Training and Defensing: A Reinforcement Learning Framework for LLM-Generated Fake Information Detection 25

Dynamic Semantic-Constrained Adversarial Training and Defens...

引用

Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information security

作者： Yuze Ding Shibin Zhang School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu Sichuan China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu Sichuan China

ISBN: (纸本)9798400713453

With the development of Large Language Models (LLMs) such as DeepSeek and GPT-4, the cost of generating false information has decreased dramatically, making detection more difficult to recognize. Traditional approaches, such as GPT-4o and chain-of-thought (CoT) frameworks, having low accuracy or efficiency. To better solve these problems, this paper introduces Dynamic Semantic Structure Rule Constrained Adversarial Training (DSC-AT), which uses balanced semantic fidelity and steganography to enhance adversarial sample optimisation, achieving an 82% deception rate. Meanwhile, the Semantic-Robust Unified Architecture (SRUA) scheme integrates text classification layer, logical verification layer and uncertainty detection layer to improve accuracy. Besides, to better train the model, we provide the Content Reinforcement Learning-based Tactical Adversarial Defence (RL-TAD) model simulates the interaction between the attacker and the defender, improves the training strategy by using backpropagation descent. Experimental results show that contrast to CoT, SRUA improves the detection accuracy to 92.1 percent and reduces the false alarm rate by 65 percent, which provided an efficient and flexible solution for identifying LLM-generated misinformation.

关键词： Chain of Thought (CoT)

来源：评论

学校读者我要写书评

暂无评论

Petri net-based illegal information flow detection method for node-chain access control model

Petri net-based illegal information flow detection method fo...

引用

2023 International Conference on Communication Network and Machine Learning, CNML 2023

作者： Li, Binyong Fang, Jie Deng, Xianhui Sheng, Yuhan Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Technology Chengdu610225 China Sichuan Institute of Computer Sciences Chengdu China School of Cybersecurity Chengdu University of Information Technology Chengdu China

ISBN: (纸本)9798400716683

To address the problem of illegal information flow in the node chain access control model constructed by the existing attribute-based access control (ABAC) model when applied to a large-scale node chain scenario with more than 100 nodes, an illegal information flow detection method is proposed for the node chain access control model based on the classical Petri net. The method introduces the reachable identity and reachable identity graph of the classical single-Token Petri net, which can analyze the illegal information flow in the ABAC-based node-chain access control model conveniently and visually. Meanwhile, it can effectively use the reachable identity state in the Petri net to detect the illegal information flow in the model. The case analysis shows that the method can effectively detect the illegal information flow appearing in the model. © 2023 ACM.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

RRCNN: Request Response-Based Convolutional Neural Network for ICS Network Traffic Anomaly Detection

引用

Computers, Materials & Continua 2023年第6期75卷 5743-5759页

作者： Yan Du Shibin Zhang Guogen Wan Daohua Zhou Jiazhong Lu Yuanyuan Huang Xiaoman Cheng Yi Zhang Peilin He Country School of Cybersecurity Chengdu University of Information TechnologyChengdu610225China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610225China DAQSOFT CO. LTDChengdu610213China Communication and Information Technology Center Petro China Southwest Oil and Gas CompanyChengdu610057China School of Computing and Information University of PittsburghPittsburgh152607PAUSA

Nowadays,industrial control system(ICS)has begun to integrate with the *** the Internet has brought convenience to ICS,it has also brought severe security *** ICS network traffic anomaly detection methods rely on statistical features manually extracted using the experience of network security *** are not aimed at the original network data,nor can they capture the potential characteristics of network ***,the following improvements were made in this study:(1)A dataset that can be used to evaluate anomaly detection algorithms is produced,which provides raw network data.(2)A request response-based convolutional neural network named RRCNN is proposed,which can be used for anomaly detection of ICS network *** of using statistical features manually extracted by security experts,this method uses the byte sequences of the original network packets directly,which can extract potential features of the network packets in greater *** regards the request packet and response packet in a session as a Request-Response Pair(RRP).The feature of RRP is extracted using a one-dimensional convolutional neural network,and then the RRP is judged to be normal or abnormal based on the extracted *** results demonstrate that this model is better than several other machine learning and neural network models,with F1,accuracy,precision,and recall above 99%.

关键词： Industrial control system(ICS) dataset network traffic anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Study on the Adversarial Sample Generation Algorithm Based on Adversarial Quantum Generation Adversarial Network

Study on the Adversarial Sample Generation Algorithm Based o...

引用

Computer Technology and Information Science (ISCTIS), International Symposium on

作者： Wen Cheng ShiBin Zhang Yusheng Lin School of Cybersecurity Sichuan Key Laboratory of advanced cryptography and system security Chengdu University of Information Technology Chengdu China

In response to the inefficiency of the existing advGAN method, which requires calculating the differences between the adversarial samples and the normal samples one by one when generating adversarial perturbations, this paper proposes a quantum adversarial sample generation algorithm (QASGA) based on adversarial quantum generative adversarial networks. First, the real samples are encoded into quantum states, then the generator G of QGAN is used to generate adversarial perturbations, which are superimposed with normal samples to obtain adversarial samples. At the same time, the SWAP-TEST method is used to calculate the similarity between all real samples and adversarial samples at once, thereby accelerating adversarial attacks. Experimental results show that the QASGA algorithm proposed in this paper can generate high-fidelity adversarial samples with a one-time similarity calculation on the IRIS dataset, and can reduce the classification accuracy of the BP neural network from 96.67% to 26.67%, verifying the effectiveness of the proposed QASGA algorithm.

关键词：

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：