scholarly journals Providing Email Privacy by Preventing Webmail from Loading Malicious XSS Payloads

2020 ◽  
Vol 10 (13) ◽  
pp. 4425
Author(s):  
Yong Fang ◽  
Yijia Xu ◽  
Peng Jia ◽  
Cheng Huang
Keyword(s):  
Modern Society ◽  
Attention Mechanism ◽  
Internet Technology ◽  
Learning Technology ◽  
Personal Privacy ◽  
Detection Model ◽  
Good Target ◽  
Communication Method ◽  
Field Information ◽  
Formal Communication

With the development of internet technology, email has become the formal communication method in modern society. Email often contains a large amount of personal privacy information, possible business agreements, and sensitive attachments, which make emails a good target for hackers. One of the most common attack method used by hackers is email XSS (Cross-site scripting). Through exploiting XSS vulnerabilities, hackers can steal identities, logging into the victim’s mailbox and stealing content directly. Therefore, this paper proposes an email XSS detection model based on deep learning technology, which can identify whether the XSS payload is carried in the email or not. Firstly, the model could extract the Sender, Receiver, Subject, Content, Attachment field information from the original email. Secondly, the email XSS corpus is formed after data processing. The Word2Vec algorithm is introduced to train the corpus and extract features for each email sample. Finally, the model uses the Bidirectional-RNN algorithm and Attention mechanism to train the email XSS detection model. In the experiment, the AUC (area under curve) value of the Bidirectional-RNN model reached 0.9979. When the Attention mechanism was added, the accuracy upper limit of the Bidirectional-RNN model was raised to 0.9936, and the loss value was reduced to 0.03.

scholarly journals A Lightweight Motional Object Behavior Prediction System Harnessing Deep Learning Technology for Embedded ADAS Applications

Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 692
Author(s):  
Wen-Chia Tsai ◽  
Jhih-Sheng Lai ◽  
Kuan-Chou Chen ◽  
Vinay M.Shivanna ◽  
Jiun-In Guo
Keyword(s):  
Embedded System ◽  
Moving Objects ◽  
Object Localization ◽  
Crossing Over ◽  
Learning Technology ◽  
Prediction System ◽  
Behavior Prediction ◽  
Detection Model ◽  
Pedestrian Crossing ◽  
Object Behavior

This paper proposes a lightweight moving object prediction system to detect and recognize pedestrian crossings, vehicles cutting-in, and vehicles ahead applying emergency brakes based on a 3D Convolution network for behavior prediction. The proposed design significantly improves the performance of the conventional 3D convolution network (C3D) adapted to predict the behaviors employing behavior recognition network capable of performing object localization, which is pivotal in detecting the numerous moving objects’ behaviors, combining and verifying the detected objects with the results of the YOLO v3 detection model with that of the proposed C3D model. Since the proposed system is a lightweight CNN model requiring far lesser parameters, it can be efficiently realized on an embedded system for real-time applications. The proposed lightweight C3D model achieves 10 frames per second (FPS) on a NVIDIA Jetson AGX Xavier and yields over 92.8% accuracy in recognizing pedestrian crossing, over 94.3% accuracy in detecting vehicle cutting-in behavior, and over 95% accuracy for vehicles applying emergency brakes.

scholarly journals Contemporary information social risks in the post-modern era

Upravlenie ◽  
2022 ◽  
Vol 9 (4) ◽  
pp. 112-120
Author(s):  
L. V. Tcerkasevich ◽  
E. A. Makarenko
Keyword(s):  
Information Technologies ◽  
Historical Memory ◽  
Modern Society ◽  
Educational Process ◽  
Internet Technology ◽  
Global Changes ◽  
Historical Events ◽  
Economic Resource ◽  
Social Risks ◽  
Depth Study

The article analyses the global social risks related to the expansion of information technologies, mass digitalisation, and the accessibility of sources of all information. The possibility of risky situations arising in different areas of society under postmodern conditions has been demonstrated. This is due to the massive spread of information and Internet technology, global changes in the structure of values of modern society, and the reassessment of a number of historical events and characters by some social groups. The focus is on the destruction of traditional mechanisms for transmitting social experience and memory and the transformation of perceptions of history through the use of virtual forms of communication. A different, own interpretation of historical events, the liberation of historical knowledge from politicisation and mythologisation can lead to risks of distortion of historical memory and even to conflicting situations of interpretation of the past. Case studies show that this, in turn, can lead to a set of risks in the economic sphere, for example: the risk of a situation of global redistribution of economic resources, the risk of losing the source of legitimacy of an economic resource, the risk of loss the reputation of a memory entity. These processes negatively affect social stability in society and distort the integrity of historical memory.Particular attention is paid to the topic of cognitive transformation risk related to the mass use of virtual media in the educational process. On the one hand, they are an effective teaching tool based on rapid search, transformation and storage of learning information. But, on the other hand, practice shows that knowledge loses its consistency and becomes “mosaic”, “clichéd”. The consequences of these processes are of a lasting nature and require further in-depth study by the scientific community, including psychologists, educators, and sociologists.

Research on Vehicle Detection Model based on Attention Mechanism

2021 ◽  
Author(s):  
Haitao Zhang ◽  
Jianmin Bao ◽  
Fei Ding ◽  
Guanyu Mi
Keyword(s):  
Vehicle Detection ◽  
Attention Mechanism ◽  
Detection Model ◽  
Model Based

scholarly journals Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism

2019 ◽  
Vol 33 ◽  
pp. 946-953 ◽  
Author(s):  
Binbin Hu ◽  
Zhiqiang Zhang ◽  
Chuan Shi ◽  
Jun Zhou ◽  
Xiaolong Li ◽  
...  
Keyword(s):  
Financial Services ◽  
Attention Mechanism ◽  
Feature Representation ◽  
Information Network ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Structure Information ◽  
Detection Model ◽  
Meta Path ◽  
Interaction Relations

As one of the major frauds in financial services, cash-out fraud is that users pursue cash gains with illegal or insincere means. Conventional solutions for the cash-out user detection are to perform subtle feature engineering for each user and then apply a classifier, such as GDBT and Neural Network. However, users in financial services have rich interaction relations, which are seldom fully exploited by conventional solutions. In this paper, with the real datasets in Ant Credit Pay of Ant Financial Services Group, we first study the cashout user detection problem and propose a novel hierarchical attention mechanism based cash-out user detection model, called HACUD. Specifically, we model different types of objects and their rich attributes and interaction relations in the scenario of credit payment service with an Attributed Heterogeneous Information Network (AHIN). The HACUD model enhances feature representation of objects through meta-path based neighbors exploiting different aspects of structure information in AHIN. Furthermore, a hierarchical attention mechanism is elaborately designed to model user’s preferences towards attributes and meta-paths. Experimental results on two real datasets show that the HACUD outperforms the state-of-the-art methods.

scholarly journals Application and Development of Computer Artificial Intelligence Technology

2019 ◽  
Vol 1 (2) ◽  
Author(s):  
Yu Zhang
Keyword(s):  
Artificial Intelligence ◽  
Science Fiction ◽  
Daily Life ◽  
Science And Technology ◽  
Modern Society ◽  
Internet Technology ◽  
Tertiary Industry ◽  
The People ◽  
Artificial Intelligence Technology ◽  
Applied Artificial Intelligence

In the development of modern society, Internet technology has been popularized and applied. Artificial intelligence technology is not only found in science fiction movies, but has been widely used in industry, tertiary industry and people’s livelihood. Under the background of rapid advancement of science and technology, computer artificial intelligence technology will play an important role in the future. Due to a series of problems in the development of computer artificial intelligence technology, it is necessary for relevant personnel to strengthen research on the application and development of computer artificial intelligence technology. The paper mainly studies the application and development of computer artificial intelligence technology, and hopes to bring more convenience to the daily life of the people.

scholarly journals Research on the Role of Mobile Learning Technology in Promoting Deep Learning of College Students

2020 ◽  
Vol 9 (6) ◽  
pp. 63
Author(s):  
Xiangsen Liu ◽  
Zhenzhen Ye ◽  
Dongmei Jiang
Keyword(s):  
College Students ◽  
Deep Learning ◽  
Mobile Learning ◽  
Modern Society ◽  
Teaching Model ◽  
Learning Technology ◽  
Social Production ◽  
Productive Force ◽  
Mobile Learning Technology

As the primary productive force, education plays a huge role in the development of modern society. Traditional educational activities mainly focus on the teaching of students’ superficial knowledge and skills, which are no longer able to meet the current society’s demand for talents. At present, it is required to promote the development of in-depth thinking of college students, stimulate their innovation and creativity, and enable students to better contribute to social production. Therefore, it is very important to introduce the concept of deep learning for college students and establish a student-based teaching model. The author mainly uses mobile learning technology to analyze the functional role of mobile learning technology in promoting deep learning activities for college students, and proposes ways to effectively grasp mobile learning technology in future university informatization education activities.

scholarly journals DeepHTTP: Anomalous HTTP Traffic Detection and Malicious Pattern Mining Based on Deep Learning

2020 ◽  
pp. 141-161
Author(s):  
Yuqi Yu ◽  
Hanbing Yan ◽  
Yuan Ma ◽  
Hao Zhou ◽  
Hongchao Guan
Keyword(s):  
Deep Learning ◽  
Web Application ◽  
Pattern Mining ◽  
Short Term Memory ◽  
Attack Detection ◽  
Attention Mechanism ◽  
Discriminative Ability ◽  
Feature Extraction Method ◽  
Detection Model ◽  
Traffic Detection

AbstractHypertext Transfer Protocol (HTTP) accounts for a large portion of Internet application-layer traffic. Since the payload of HTTP traffic can record website status and user request information, many studies use HTTP protocol traffic for web application attack detection. In this work, we propose DeepHTTP, an HTTP traffic detection framework based on deep learning. Unlike previous studies, this framework not only performs malicious traffic detection but also uses the deep learning model to mine malicious fields of the traffic payload. The detection model is called AT-Bi-LSTM, which is based on Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism. The attention mechanism can improve the discriminative ability and make the result interpretable. To enhance the generalization ability of the model, this paper proposes a novel feature extraction method. Experiments show that DeepHTTP has an excellent performance in malicious traffic discrimination and pattern mining.

scholarly journals Detection and Recognition of SAR Small Ship Objects Using Deep Neural Network

2019 ◽  
Vol 37 (3) ◽  
pp. 587-593
Author(s):  
Songjie Wei ◽  
Pengfei Jiang ◽  
Qiuzhuang Yuan ◽  
Meilin Liu
Keyword(s):  
Object Detection ◽  
Target Detection ◽  
Recognition Performance ◽  
Learning Technology ◽  
Small Target ◽  
Sar Images ◽  
Small Target Detection ◽  
Detection Model ◽  
Small Ship ◽  
Detection And Recognition

Synthetic aperture radar(SAR) ship target detection plays an increasingly important role in marine monitoring. Aimed at the problems of recognizing small size of ship targets in SAR images and the inability of traditional methods to extract fine target features due to external disturbances, we propose an improved SAR small target detection model based on the deep learning technology. The proposed model mainly consists of two parts:region proposal network(RPN) and object detection network. Firstly, a CNN model is designed and trained to accurately identify small ship targets. Then, the model is used to initialize the parameters of the shared feature extraction layer. Last, we train the proposed object detection model using a self-collected Sentinel-1 SAR small target dataset. The experimental results show that the proposed target detection model has better detection and recognition performance and anti-interference ability for small ship scalable targets in SAR images, and has certain reference value for the research of small target detection in SAR images.

Teaching Medical Statistics Over the Internet

2011 ◽  
pp. 1437-1444
Author(s):  
Rachael Knight ◽  
Kate Whittington ◽  
W. Chris L. Ford ◽  
Julian M. Jenkins
Keyword(s):  
Reproductive Medicine ◽  
Online Teaching ◽  
Statistics Education ◽  
Postgraduate Education ◽  
Training Programme ◽  
Internet Technology ◽  
The Internet ◽  
Learning Technology ◽  
University Of Bristol ◽  
The University

The potential for computers to assist learning has been recognised for many years (Jenkins, 1997), with reproductive medicine benefiting greatly from Internet technology (Jenkins, 1999). Following a detailed survey of information technology facilities and skills for postgraduate education (Draycott, 1999), a pilot Internet training programme in reproductive medicine demonstrated effective methods to deliver online teaching (Jenkins, 2001). Based on this experience, in 2001 the Obstetrics and Gynaecology in the University of Bristol, U.K. launched a postgraduate masters course in human reproduction and development, delivered principally over the Internet (Jenkins, 2002). This course has been under continuous evaluation and development since its launch, refining the application of learning technology to most appropriately meet students’ needs (Cahill, 2003). A particularly challenging module of the course considers research methods and statistics. This module was independently evaluated from both a student and tutor perspective, with the objective of identifying learning priorities and optimal educational methodology. This article presents strengths and weaknesses of delivering statistics education online, considering how best to develop this in the future.

scholarly journals Attention-Based Automated Feature Extraction for Malware Analysis

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2893 ◽  
Author(s):  
Sunoh Choi ◽  
Jangseong Bae ◽  
Changki Lee ◽  
Youngsoo Kim ◽  
Jonghyun Kim
Keyword(s):  
Feature Extraction ◽  
Short Term Memory ◽  
Attention Mechanism ◽  
Detection Methods ◽  
Malware Analysis ◽  
Feature Extraction Method ◽  
Detection Model ◽  
System Calls ◽  
Long Short Term Memory ◽  
Program Interface

Every day, hundreds of thousands of malicious files are created to exploit zero-day vulnerabilities. Existing pattern-based antivirus solutions face difficulties in coping with such a large number of new malicious files. To solve this problem, artificial intelligence (AI)-based malicious file detection methods have been proposed. However, even if we can detect malicious files with high accuracy using deep learning, it is difficult to identify why files are malicious. In this study, we propose a malicious file feature extraction method based on attention mechanism. First, by adapting the attention mechanism, we can identify application program interface (API) system calls that are more important than others for determining whether a file is malicious. Second, we confirm that this approach yields an accuracy that is approximately 12% and 5% higher than a conventional AI-based detection model using convolutional neural networks and skip-connected long short-term memory-based detection model, respectively.

Sign in / Sign up

Export Citation Format

Share Document