Deep Neural Network with Stacked Denoise Auto Encoder for Phishing Detection

Stacked autoencoder (SAE) is hard to achieve satisfactory performance, when input data are complex and non-stationary. Besides, the identification performance of recurrent neural network (RNN) may decrease rapidly under noisy environment. In order to deal with these problems, a novel hybrid deep neural network (DNN) based on stacked denoising autoencoder (SDAE) and gated recurrent unit neural network (GRUNN) is presented. First, the structure of the presented hybrid DNN is given. The hybrid DNN contains a SDAE, a GRUNN, and a softmax classifier. Then, the training algorithm based on action discovery (AD) is proposed to train the presented hybrid DNN. The experimental studies indicate the presented hybrid DNN processes strong anti-noise ability and adaptability to time-varying signals.

Extracting and inserting knowledge into stacked denoising auto-encoders

Phishing is a type of social engineering attack with an intention to steal user data, including login credentials and credit card numbers, leading to financial losses for both organizations and individuals. It occurs when an attacker, pretending as a trusted entity, lure a victim into click on a link or attachment in an email, or in a text message. Phishing is often launched via email messages or text messages over social networks. Previous research has revealed that phishing attacks can be identified just by looking at uniform resource locator (URLs). Identifying the techniques which are used by phishers to mimic a phishing URL is rather a challenging issue. At present, we have limited knowledge and understanding of how cyber‐criminals attempt to mimic URLs with the same look and feel of the legitimate ones, to entice people into clicking links. Therefore, this paper investigates the feature selection of phishing URLs (uniform resource locators), aiming to explore the strategies employed by phishers to mimic URLs that can obviously trick people into clicking links. We employed an information gain (IG) and Chi‐Squared feature selection methods in machine learning (ML) on a phishing dataset. The dataset contains a total of 48 features extracted from 5000 phishing and another 5000 legitimate URL from web pages downloaded from January to May 2015 and from May to June 2017. Our results revealed that there were 10 techniques that phishers used to mimic URLs to manipulate humans into clicking links. Identifying these phishing URL manipulation techniques would certainly help to educate individuals and organizations and keep them safe from phishing attacks. In addition, the findings of this research will also help develop anti‐phishing tools, framework or browser plugins for phishing prevention.

In this paper, the features of HTML and XML were compared, and expounds the necessity of transition from HTML to XML, and finally introduces document conversion, XHTML conversion and intelligent instead of three kinds of HTML to XML conversion method. Keyword: HTML;XML;conversion method;XHTML Characteristics of HTML HTML (Hypertext Markup Language) is a universal language for creating Webpage and to release information, it is YISHION text stored in the form of organization, to label definition document. Provided the cross plat form file sharing. In the HTML document, can be embedded in other objects, such as electronic forms, video, audio and various applications and so on, through the uniform resource locator can realize the hypertext links between Web nodes. HTML has the following features, format and grammar is relatively simple, easy to learn, will the data with some control markers, even if no programming experience can easily use HTML to design Webpage; and all of the control tag HTML is fixed [1], the number is limited, provides functions and related properties the setting is fixed, easy to remember; rules more flexible, such as the control of English marker size marker to write in no difference. In addition, the control flag must have the end tag corresponding to no strict requirements. Need the simplicity of HTML is more suitable for low cost information publishing; HTML as Web common information description method of strong universality, can realize different platform document sharing; to create more flexible, HTML document is a plain text file, can use a variety of editing tools for creating. The major disadvantage of HTML is: (1) Performance is too simple. (2) Link easily broken, chain destination address changes, chain source cannot automatically correct. (3) The flowers during the retrieval time are longer, the retrieved content targeted poor, and many returned results. (4) Poor scalability, HTML tag set is fixed, not to allow users to define their International Symposium on Computers & Informatics (ISCI 2015) © 2015. The authors Published by Atlantis Press 64 own identity. (5) The lack of semantics, HTML is a marker, it will not reveal the nature of the information content, and the computer cannot know the exact meaning of each section of text. HTML and XML are used for the network information organization and communication, are in the form of texts written in storage, and are structured information based on international standards [2]. But HTML only shows data seems to be what kind of, and the XML is that data is what mean. Using XML can create their own tags, these tags can more accurately describe the user what they want, but HTML can not be used to define a new application, and this is the biggest difference between XML and HTML. XML has overcome some limitations of the HTML, has the broad application prospect. The necessity of transformation Most of the current Webpage still is mainly composed of HTML. HTML of the inherent shortcomings of the original network information organization mode can't meet the requirements of the development of the new. Because the relevant development of the XML technology continues to mature, more and more websites gradually in XML design. In this process, not only will the new content is stored in XML format and transmission, but also consider compatible with the original data, so it is necessary to convert existing HTML Webpage into XML data form more flexible processing and application. At the same time, to the previous accumulated HTML documents continue to play a role in the new environment, the XML conversion is undoubtedly a solution. HTML to XML conversion is helpful for Webpage information integration, extraction, retrieval, filtering or mining analysis. (1) Facilitate the information integration of heterogeneous system under Network Environment In the network environment, because of the existence of the system platform and database operation of heterogeneous, leading to the exchange of information and work with difficulty. One of the data exchange between heterogeneous systems is to adopt a unified information exchange format. XML because of its custom and scalability advantages [3], which is convenient for expressing various types of data between heterogeneous databases, and can be used as middleware, unify the data interface, convenient for the exchange of information between different databases and colleagues. XML can be used to construct the data layer integration, will transform the source data into the data integration, simplification of integration system query translation, query mechanisms provide unified multi data source for the user, in a unified way using a variety of data from different sources of data, different shielding each data source in the structure, running environment on the. (2) The organization and management for network information

Life prediction of lithium-ion batteries based on stacked denoising autoencoders

In recent years, Recommender System (RS) research work has covered a wide variety of Artificial Intelligence techniques, ranging from traditional Matrix Factorization (MF) to complex Deep Neural Networks (DNN). Traditional Collaborative Filtering (CF) recommendation methods such as MF, have limited learning capabilities as it only considers the linear combination between user and item vectors. For learning non-linear relationships, methods like Neural Collaborative Filtering (NCF) incorporate DNN into CF methods. Though, CF methods still suffer from cold start and data sparsity. This paper proposes an improved hybrid-based RS, namely Neural Matrix Factorization++ (NeuMF++), for effectively learning user and item features to improve recommendation accuracy and alleviate cold start and data sparsity. NeuMF++ is proposed by incorporating effective latent representation into NeuMF via Stacked Denoising Autoencoders (SDAE). NeuMF++ can also be seen as the fusion of GMF++ and MLP++. NeuMF is an NCF framework which associates with GMF (Generalized Matrix Factorization) and MLP (Multilayer Perceptrons). NeuMF achieves state-of-the-art results due to the integration of GMF linearity and MLP non-linearity. Concurrently, incorporating latent representations has shown tremendous improvement in GMF and MLP, which result in GMF++ and MLP++. Latent representation obtained through the SDAEs' latent space allows NeuMF++ to effectively learn user and item features, significantly enhancing its learning capability. However, sharing feature extractions among GMF++ and MLP++ in NeuMF++ might hinder its performance. Hence, allowing GMF++ and MLP++ to learn separate features provides more flexibility and greatly improves its performance. Experiments performed on a real-world dataset have demonstrated that NeuMF++ achieves an outstanding result of a test root-mean-square error of 0.8681. In future work, we can extend NeuMF++ by introducing other auxiliary information like text or images. Different neural network building blocks can also be integrated into NeuMF++ to form a more robust recommendation model.

Probabilistic power flow with topology changes based on deep neural network

Phishing is an attempt by an individual or a group of person to steal personal information such as password, banking account and credit card information, etc. Most of these phishing web pages look similar to the real web pages in terms of website interface and uniform resource locator (URL) address. Many techniques have been proposed to detect phishing websites, such as Blacklist-based technique, Heuristic-based technique, etc. However, these techniques are still inefficient. While Blacklist-based techniques cannot detect the phishing sites that are not in the blacklist database, the weights of the heuristic in the heuristic-based approach significantly depend on the statistics from the training dataset. Therefore, a new phishing detection approach in which either the new phishing websites can be detected or the weights of the heuristic are derived objectively is necessary. In this paper, an efficient approach for detecting phishing websites based on the single-layer neural network is proposed. Specifically, the proposed technique calculates the value of heuristics objectively. Then, the weights of heuristic are generated by a single-layer neural network. The proposed technique is evaluated with a dataset of 11,660 phishing sites and 10,000 legitimate sites. The results show that the technique can detect over 98% phishing sites.

Software defect prediction technology plays an important role in ensuring software quality. The traditional software defect prediction model can only perform “shallow learning” and cannot perform deep mining of data features. Aiming at this problem, we use the stacked denoising auto-encoder (SDAE) to superimpose into deep neural network. First, the deep network model was built through the stacked layers of denoising auto-encoder (DAE), then the unsupervised method was used to train each layer in turn with noised input for more robust expression, characteristics were learnt supervised by back propagation (BP) neural network and the whole net was optimized by using error back propagation. Simulation experiments prove that the prediction accuracy of our SDAE model is significantly improved compared with the traditional SVM and KNN prediction model.

Heart disease is a prevalent and life-threatening condition that affects a significant portion of the global population. Preventing negative consequences and better health outcomes may be greatly helped by early identification and precise prognosis of cardiac disease. Electrocardiogram (ECG) is the important apparatus which is used for diagnosticians of assessment of cardiogram in the clinical. This will Owing to its ability to learn complicated patterns from massive volumes of data, deep neural networks (DNNs) have recently emerged as strong tools for medical diagnostic and prediction tasks. In this part of research, people investigate the use of deep neural networks for cardiac illness forecasting which is easy way for analysis of cardio problem. We analyse various studies and approaches that have utilized Deep Neural Networks for heart disease prediction. This study gives us whole sheds light on the evolution of methods that use in deep neural networks to forecast cardiac issues. The findings from this survey can guide researchers and practitioners in designing and implementing effective DNN models for heart disease prediction, ultimately contributing to improved clinical decision-making and patient care.In this study, we will examine the various DNN techniques, including CNNs (Convolutional Neural Networks) and Stack Denoising Auto encoder, Deep Belief Network, Recurrent Neural Network (RNN), Long Short term Memory (LSTM) and Gated Recurrent Unit (GRU).

Heartbeat classification is a crucial step for arrhythmia diagnosis during electrocardiographic (ECG) analysis. The new scenario of wireless body sensor network- (WBSN-) enabled ECG monitoring puts forward a higher-level demand for this traditional ECG analysis task. Previously reported methods mainly addressed this requirement with the applications of a shallow structured classifier and expert-designed features. In this study, modified frequency slice wavelet transform (MFSWT) was firstly employed to produce the time-frequency image for heartbeat signal. Then the deep learning (DL) method was performed for the heartbeat classification. Here, we proposed a novel model incorporating automatic feature abstraction and a deep neural network (DNN) classifier. Features were automatically abstracted by the stacked denoising auto-encoder (SDA) from the transferred time-frequency image. DNN classifier was constructed by an encoder layer of SDA and a softmax layer. In addition, a deterministic patient-specific heartbeat classifier was achieved by fine-tuning on heartbeat samples, which included a small subset of individual samples. The performance of the proposed model was evaluated on the MIT-BIH arrhythmia database. Results showed that an overall accuracy of 97.5% was achieved using the proposed model, confirming that the proposed DNN model is a powerful tool for heartbeat pattern recognition.

Computer assisted automatic smart pattern analysis of cancer affected pixel structure takes critical role in pre-interventional decision making for oral cancer treatment. Internet of Things (IoT) in healthcare systems is now emerging solution for modern e-healthcare system to provide high quality medical care. In this research work, we proposed a novel method which utilizes a modified vesselness measurement and a Deep Convolutional Neural Network (DCNN) to identify the oral cancer region structure in IoT based smart healthcare system. The robust vesselness filtering scheme handles noise while reserving small structures, while the CNN framework considerably improves classification accuracy by deblurring focused region of interest (ROI) through integrating with multi-dimensional information from feature vector selection step. The marked feature vector points are extracted from each connected component in the region and used as input for training the CNN. During classification, each connected part is individually analysed using the trained DCNN by considering the feature vector values that belong to its region. For a training of 1500 image dataset, an accuracy of 96.8% and sensitivity of 92% is obtained. Hence, the results of this work validate that the proposed algorithm is effective and accurate in terms of classification of oral cancer region in accurate decision making. The developed system can be used in IoT based diagnosis in health care systems, where accuracy and real time diagnosis are essential.

Aimed at the problem that the traditional feature selection method extracts the feature items and the filtering accuracy is degraded in the Chinese spam filtering process, this paper proposes a Chinese spam filtering method based on Stacked Denoising Autoencoder (SDA). Firstly, use the Continuous Bag-of-Words (CBOW) model training the Word2vec tool set for the processed corpus to transform word segments into vectors; the inputs are the word vectors; then apply the Stacked Denoising Autoencoder (SDA) to effectively extract the features text in unsupervised learning. Finally, the improved softmax classifier is used for regression classification. The test was carried out on the TREC06C dataset, the experimental results show that compared with Bayesian model, KNN classification algorithm and traditional Stacked Denoising Autoencoder, the accuracy, precision, recall, and f1 score of the method reached 93.5%, 94.8%, 92% and 93.2%, and had better dichotomous effect and robustness in the application.

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers' data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts' annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.

Detecting faces in the wild is a challenging problem due to large visual variations introduced by uncontrolled facial expressions, head pose, illumination and so on. Employing strong classifier and designing more discriminative visual features are two main approaches to overcoming such difficulties. Notably, Deep Neural Network (DNN) based methods have been found to outperform most traditional detectors in a multitude of studies, employing deep network structures and complex training procedures. In this work, we propose a novel method that uses stacked denoising autoencoders (SdA) for feature extraction and random forests (RF) for object-background classification in a classical cascading framework. This architecture allows much simpler neural network structures, resulting in efficient training and detection. The proposed face detector was evaluated on two publicly available datasets and produced promising results.