检索结果-内蒙古大学图书馆

LLM-AE-MP: Web Attack Detection Using a Large Language Model with autoencoder and Multilayer Perceptron

EXPERT SYSTEMS WITH APPLICATIONS 2025年 274卷

作者： Yang, Jing Wu, Yuangui Yuan, Yuping Xue, Haozhong Bourouis, Sami Abdel-Salam, Mahmoud Prajapat, Sunil Por, Lip Yee Univ Malaya Fac Comp Sci & Informat Technol Dept Comp Syst & Technol Kuala Lumpur 50603 Malaysia Jilin Univ Sch Software Changchun 130012 Jilin Province Peoples R China Radio Film & Televis Design & Res Inst Co Ltd Informat & Network Inst Beijing 100045 Peoples R China NYU Tandon Sch Engn New York NY 11101 USA Taif Univ Coll Comp & Informat Technol Dept Informat Technol POB 11099 Taif 21944 Saudi Arabia Mansoura Univ Fac Comp & Informat Sci Mansoura 35516 Egypt Cent Univ Himachal Pradesh Srinivasa Ramanujan Dept Math Dharamshala 176215 India

Web applications store sensitive data, making them prime targets for cybercriminals and posing national security risks. This study introduces a new approach to distinguishing legitimate and malicious hypertext transfer protocol (HTTP) requests using an autoencoder (AE). The integration of AE allows for efficient feature distillation, enhancing the sensitivity of the model to anomalies in HTTP traffic. The AE framework is combined with a transductive long short-term memory (TLSTM) network, which is trained with an advanced generative adversarial network (GAN). Using GAN promotes an adaptive learning environment, significantly boosting the robustness and generalizability of our method against evolving web attack vectors. TLSTM uses transductive learning to focus on data points near the test set, improving the adaptability of the model to outperform traditional LSTM models. In our GAN, the generator purposely excludes gradients from the most influential batch elements, improving the ability of the model to generate diverse and generalized outputs. After training the AE, its latent representations are passed to a multilayer perceptron (MLP) for detection tasks. To address the imbalanced classification in MLP, we use a reinforcement learning (RL) strategy. The RL approach strategically adjusts incentives, enhancing the performance of the model in identifying less frequent but critical malicious instances, thereby supporting a balanced security assessment. Our evaluations using the CSIC 2010 (Spanish National Research Council 2010), FWAF (web application firewall), and HttpParams datasets show that our method outperforms existing techniques, achieving (Accuracy, F-measure, geometric mean (G-means), and area under the curve (AUC)) reaching (90.937%, 89.755%, 88.446%, 0.838), (89.055, 90.663%, 88.334%, 0.847) and (92.242%, 93.774%, 91.356%, 0.897), respectively. Moreover, our model achieves efficient runtime and memory usage across the datasets, providing a practical soluti

关键词： Web attack Anomalous request autoencoder Long short-term memory Generative adversarial network Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Application of latent Dirichlet allocation and autoencoder to real estate datasets

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-24页

作者： Gu, Runhe Lin, Luchun Changzhou Univ Sch Comp Sci & Artificial Intelligence Aliyun Sch Big Data Sch Software 2468 Yanzheng West Ave Changzhou 213159 Jiangsu Peoples R China

At present, there are too many types and numbers of real estate features in the real estate market, and it is difficult to effectively recommend real estate to customers with more complicated needs. The datasets of real estate often encompass a wide array of features, including categories, numerical values, and textual descriptions, which complicates the process of delivering precise and satisfactory recommendations. To address this issue, a cluster-based hybrid method combining latent Dirichlet allocation and autoencoder is proposed in this paper. It can effectively improve the early input of clustering by the two-stage feature extraction of the data through the topic model and the autoencoder. Experimental findings demonstrate that our hybrid method surpasses standalone LDA and autoencoder, as well as other conventional clustering algorithms. The combined results of Silhouette coefficient, DB index, and CH index are significantly better than the results of traditional clustering. Moreover, we conduct a comprehensive analysis of the results, emphasizing the benefits of our approach in managing multi-type features, encompassing categorical, numerical, and string data. It is anticipated that this research will contribute valuable insights into the field of recommendation systems.

关键词： Latent Dirichlet allocation autoencoder Hybrid method Real estate recommendation Deeping clustering

来源：评论

学校读者我要写书评

暂无评论

Data-driven strategy: A robust battery anomaly detection method for short circuit fault based on mixed features and autoencoder

引用

APPLIED ENERGY 2025年 382卷

作者： Zhao, Hongyu Zhang, Chengzhong Liao, Chenglin Wang, Liye Liu, Weilong Wang, Lifang Chinese Acad Sci Inst Elect Engn Key Lab High Dens Electromagnet Power & Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Sifang Automat Co Ltd 9 Shangdi Fourth St Beijing 100085 Peoples R China

The anomaly detection of lithium-ion batteries for short circuit (SC) faults is crucial to ensure the safety of the energy storage system. Compared to the diagnosis fault of packs, individual cell fault diagnosis lacks a reference target, leading to difficulties in effectively detecting whether an abnormality exists. In this paper, a data-driven detection method based on the autoencoder strategy is proposed for early detection of battery faults without pack information. Within, the autoencoder strategy is used to reconstruct the voltage and detect potential faults. Using the generative adversarial network (GAN) framework for model training reduces its overfitting and improves efficiency. In addition, during anomaly detection, due to the lack of battery pack reference, some abnormal voltage changes due to current variations can lead to misdiagnosis. To address this concern, the mixed features input is proposed to reduce the misdiagnosis rate, which incorporates the equivalent circuit model parameters. Experiments demonstrate that the proposed method can accurately detect SC faults, in particular, it can detect some moderate or weak faults within 1.6 h. Compared to other methods, this method has better effectiveness and robustness. The method proposed in this paper is in line with the development trend for big data and opens up new perspectives for the development of energy storage safety technology.

关键词： Anomaly detection lithium-ion batteries Short circuit faults Mixed features autoencoder Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Pattern-Based Attention Recurrent autoencoder for Anomaly Detection in Air Quality Sensor Networks

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第6期11卷 6372-6381页

作者： Allka, Xhensilda Ferrer-Cid, Pau Barcelo-Ordinas, Jose M. Garcia-Vidal, Jorge Univ Politecn Catalunya UPC Dept Comp Architecture Barcelona 08034 Spain

Sensor networks play an essential role in today's air quality monitoring platforms. Nevertheless, sensors often malfunction, leading to data anomalies. In this paper, an unsupervised pattern-based attention recurrent autoencoder for anomaly detection (PARAAD) is proposed to detect and locate anomalies in a network of air quality sensors. The novelty of the proposal lies in the use of temporal patterns, i.e., blocks of data, instead of point values. By looking at temporal patterns and through an attention mechanism, the architecture captures data dependencies in the feature space and latent space, enhancing the model's ability to focus on the most relevant parts. Its performance is evaluated with two categories of anomalies, bias fault and drift anomalies, and compared with baseline models such as a feed-forward autoencoder and a transformer architecture, as well as with models not based on temporal patterns. The results show that PARAAD achieves anomalous sensor detection and localization rates higher than 80%, outperforming existing baseline models in air quality sensor networks for both bias and drift faults.

关键词： Anomaly detection Monitoring Air quality Atmospheric modeling Data models Correlation Attention mechanisms monitoring networks anomaly detection Internet of Things autoencoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Enhancing image classification using adaptive convolutional autoencoder-based snow avalanches algorithm

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第10期18卷 6867-6879页

作者： Dhiravidachelvi, E. Devadas, T. Joshva Kumar, P. J. Sathish Pandi, S. Senthil Mohamed Sathak Engn Coll Dept Elect & Commun Engn Kilakarai Tamil Nadu India VIT Univ Sch Comp Sci & Engn Vellore India Panimalar Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India Rajalakshmi Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India

The disease that causes a large number of deaths annually across the world is brain cancer and it has become an important research topic in the field of medical image processing in recent times. There are various techniques for the detection of brain tumors (BT) but magnetic resonance imaging (MRI) diagnosing techniques show superior performance in the prognosis and examination of brain tumors in the early stages. The manual detection of brain tumors by radiologists leads to many limitations like errors and lack of detection accuracy. Hence, there is a need for computer-aided diagnostic techniques to help radiologists in detecting brain tumors accurately from the MRI images. To make this process more effective, the implementation of an automated technique is a preferred choice. In this paper, an effective detection and classification technique Adaptive convolutional autoencoder-based Snow Avalanches (ACAE-SA) Algorithm is proposed. This algorithm comprises an Adaptive CNN component and an autoencoder to detect and categorize BT from the MRI images. To mitigate the computational complexities in these components a Snow Avalanches algorithm is integrated into this work as an optimization technique. For the validation of the proposed architecture two MRI image datasets namely figshare and BraTS 2018 are used. The proposed technique proved its effectiveness in the detection and classification of brain tumors from the MRI images and outperformed the state-of-the-art techniques.

关键词： Adaptive CNN autoencoder Brain tumor Medical image processing MRI images Snow avalanches algorithm

来源：评论

学校读者我要写书评

暂无评论

GenCoder: A Novel Convolutional Neural Network Based autoencoder for Genomic Sequence Data Compression

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第3期21卷 405-415页

作者： Sheena, K. S. Nair, Madhu S. Cochin Univ Sci & Technol Dept Comp Sci Artificial Intelligence & Comp Vis Lab Kochi 682022 India

Revolutionary advances in DNA sequencing technologies fundamentally change the nature of genomics. Today's sequencing technologies have opened into an outburst in genomic data volume. These data can be used in various applications where long-term storage and analysis of genomic sequence data are required. Data-specific compression algorithms can effectively manage a large volume of data. In recent times, deep learning has achieved great success in many compression tools and is gradually being used in genomic sequence compression. Significantly, autoencoder has been applied in dimensionality reduction, compact representations of data, and generative model learning. It can use convolutional layers to learn essential features from input data, which is better for image and series data. autoencoder reconstructs the input data with some loss of information. Since accuracy is critical in genomic data, compressed genomic data must be decompressed without any information loss. We introduce a new scheme to address the loss incurred in the decompressed data of the autoencoder. This paper proposes a novel algorithm called GenCoder for reference-free compression of genomic sequences using a convolutional autoencoder and regenerating the genomic sequences from a latent code produced by the autoencoder, and retrieving original data losslessly. Performance evaluation is conducted on various genomes and benchmarked datasets. The experimental results on the tested data demonstrate that the deep learning model used in the proposed compression algorithm generalizes well for genomic sequence data and achieves a compression gain of 27% over the best state-of-the-art method.

关键词： Genomics Bioinformatics Sequential analysis DNA Costs Compressors Encoding Genomic sequence deep learning autoencoder FASTA lossless compression

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-like deep NMF representation learning algorithm for clustering

引用

KNOWLEDGE-BASED SYSTEMS 2024年 305卷

作者： Wang, Dexian Zhang, Pengfei Deng, Ping Wu, Qiaofeng Chen, Wei Jiang, Tao Huang, Wei Li, Tianrui Chengdu Univ Tradit Chinese Med Chengdu 611137 Peoples R China Xihua Univ Sch Comp & Software Engn Chengdu 610039 Peoples R China Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data Appl Chengdu 611756 Peoples R China Mfg Ind Chains Collaborat & Informat Support Techn Chengdu 611756 Peoples R China

Clustering plays a crucial role in the field of data mining, where deep non-negative matrix factorization (NMF) has attracted significant attention due to its effective data representation. However, deep matrix factorization based on autoencoder is typically constructed using multi-layer matrix factorization, which ignores nonlinear mapping and lacks learning rate to guide the update. To address these issues, this paper proposes an autoencoder-like deep NMF representation learning (ADNRL) algorithm for clustering. First, according to the principle of autoencoder, construct the objective function based on NMF. Then, decouple the elements in the matrix and apply the nonlinear activation function to enforce non-negative constraints on the elements. Subsequently, the gradient values corresponding to the elements update guided by the learning rate are transformed into the weight values. This weight values are combined with the activation function to construct the ADNRL deep network, and the objective function is minimized through the learning of the network. Finally, extensive experiments are conducted on eight datasets, and the results demonstrate the superior performance of ADNRL.

关键词： Non-negative matrix factorization Clustering autoencoder Deep learning

来源：评论

学校读者我要写书评

暂无评论

Radar pre-sorting algorithm based on autoencoder and LSTM

引用

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS 2024年 187卷

作者： Jiang, Yilin Shi, Shaoxiong Zhang, Fangyuan Huang, Wuqi Harbin Engn Univ Coll Informat & Commun Engn Harbin 150001 Peoples R China Harbin Univ Sci & Technol Harbin Peoples R China AVIC United Technol Ctr Electromagnet Spectrum Col Harbin Peoples R China

As the electromagnetic environment becomes increasingly complex, most current radar signal sorting methods are unsustainable. They often perform poorly when dealing with unknown radar types and low-frequency radar pulse data. This paper introduces a radar pre-sorting algorithm based on autoencoder and LSTM. The algorithm utilizes multi-dimensional information such as pulse width, carrier frequency, and time of arrival. The autoencoder network is employed to achieve automatic feature extraction and clustering, enhancing the extraction of latent features in the data. The proposed network model mainly consists of three parts: an encoding module composed of a convolutional neural network (CNN), a feature aggregation module composed of long short-term memory (LSTM), and a decoding module obtained through a convolutional autoencoder, referred to as CLDE (CNN-LSTM-Decode). The encoding module extracts features from multi-dimensional data to obtain compressed features, the feature accumulation module processes the compressed features, further extracting hidden features between pulses. Subsequently, the decoding module determines the pulse modulation type of each pulse, achieving the purpose of radar pulse signal pre-sorting. Simulation results show that this network structure effectively pre-classifies unknown radar signals and has a high recognition rate for low-frequency pulses. Additionally, CLDE exhibits high reliability and stability in environments with pulse loss.

关键词： CLDE Low-frequency autoencoder LSTM

来源：评论

学校读者我要写书评

暂无评论

LTScoder: Long-Term Time Series Forecasting Based on a Linear autoencoder Architecture

引用

IEEE ACCESS 2024年 12卷 98623-98633页

作者： Kim, Geunyong Yoo, Hark Kim, Chorwon Kim, Ryangsoo Kim, Sungchang Elect & Telecommun Res Inst Honam Res Div Gwangju 34129 South Korea

A long-term time series forecasting (LTSF) model named LTScoder based on a linear autoencoder architecture is presented in this paper. LTScoder performs feature extraction through an encoder to generate a latent vector and conducts time series prediction based on this latent vector through a decoder. The latent vector, which is mapped to a lower dimensionality by extracting features from the input time series, not only reduces the complexity of the linear regression operations performed in the decoder but also captures essential temporal dependencies for forecasting. Experimental results conducted on popular univariate and multivariate datasets with diverse patterns demonstrate that LTScoder achieves up to 16.95 times faster inference time than PatchTST, the state-of-the-art transformer-based model. LTScoder exhibits minimal degradation in prediction accuracy while using only 2.11% of PatchTST's parameters. Furthermore, we show that the LTScoder model is well-suited for edge computing in time series data prediction tasks. The architectural flexibility of LTScoder allows the encoder and decoder to be deployed in separate systems, enhancing scalability and efficiency. We measure the performance of LTScoder in terms of its prediction accuracy and computational complexity using the ETRI edge gateway system.

关键词： Time series analysis Predictive models Transformers Data models Computational modeling Forecasting Feature extraction autoencoders autoencoder edge computing long-term time series forecasting LTScoder

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-Based Hybrid Detection Model for Intrusion Detection With Small-Sample Problem

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2024年第2期21卷 2402-2412页

作者： Wei, Nan Yin, Lihua Tan, Jingyi Ruan, Chuhong Yin, Chuang Sun, Zhe Luo, Xi Guangzhou Univ Cyberspace Inst Adv Technol Guangzhou 510006 Guangdong Peoples R China Guangzhou Xinhua Univ Dept Informat Resource Management Guangzhou 510520 Guangdong Peoples R China

Cyber-attacks have become more frequent, targeted, and complex as the exponential growth in computer networks and the development of Internet of Things (IoT). Network intrusion detection system (NIDS) is an important and essential tool to protect network environments. However, the low performance of a NIDS against small malicious samples has seriously threatened the security of networks, thus directly leading to the loss of personal property and national interests. Given this, we propose an auto encoder-based hybrid detection model, abbreviated as AHDM, for the intrusion detection with small-sample problem. AHDM has a dual classifier framework. It trains first neural network based on the encoding features obtained from the autoencoder feature enhancement algorithm to detect small-sample malicious traffic. It trains second neural network using the original features to detect normal traffic and large-sample malicious traffic. The final detection result of malicious traffic is obtained by combining the detection results of the two neural networks. In experiments, we use three classic datasets (KDD CUP 99, CIC-IDS-2017, and IOT-23) and simulate the malicious traffic detection targeting extremely small-sample malicious traffic. The results show that AHDM has a higher detection rate for small-sample malicious traffic compared to the advanced detection models (DNN and ACID). In the IOT-23 dataset, the AHDM model shows an absolute advantage in detecting DDoS type of malicious traffic, with a detection rate of 0.71, which is much higher than the DNN (0.14) and ACID (0.14) models.

关键词： Malicious traffic detection autoencoder IOT-23 network intrusion detection system small-sample dataset

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：