A Deep Learning Method for Android Application Classification Using Semantic Features

Wang, Zhiqiang; Li, Gefei; Zhuo, Zihan; Ren, Xiaorui; Lin, Yuheng; Gu, Jieming

doi:10.1155/2022/1289175

Cited by 8 publications

(3 citation statements)

References 33 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, more and more attackers take Android as the primary target. Wang et al [78], designed an Android application classification model based on multiple semantic features. Key features help identify dangerous behaviours in unknown applications more effectively.…”

Section: Automated Featuresmentioning

confidence: 99%

Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review

Hussain,

Razak,

Firdaus

2023

JCSANDM

View full text Add to dashboard Cite

Globally extensive digital revolutions involved with every process related to human progress can easily create the critical issues in security aspects. This is promoted due to the important factors like financial crises and geographical connectivity in worse condition of the nations. By this fact, the authors are well motivated to present a precise literature on malware detection with deep learning approach. In this literature, the basic overview includes the nature of nature of malware detection i.e., static, dynamic, and hybrid approach. Another major component of this articles is the investigation of the backgrounds from recently published and highly cited state-of-the-arts on malware detection, prevention and prediction with deep learning frameworks. The technologies engaged in providing solutions are utilized from AI based frameworks like machine learning, deep learning, and hybrid frameworks. The main motivations to produce this article is to portrait clear pictures of the option challenging issues and corresponding solution for developing robust malware-free devices. In the lack of a robust malware-free devices, highly growing geographical and financial disputes at wide globes can be extensively provoked by malicious groups. Therefore, exceptionally high demand of the malware detection devices requires a very strong recommendation to ensure the security of a nation. In terms preventing and recovery, Zero-day threats can be handled by recent methodology used in deep learning. In the conclusion, we also explored and investigated the future patterns of malware and how deals with in upcoming years. Such review may extend towards the development of IoT based applications used many fields such as medical devices, home appliances, academic systems.

show abstract

Section: Automated Featuresmentioning

confidence: 99%

Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review

Hussain,

Razak,

Firdaus

2023

JCSANDM

View full text Add to dashboard Cite

show abstract

“…Computer technology has given rise to a variety of digital venues, including instructional programmes, internet pages, and online classrooms [3]. These systems include multimedia content, activities, and educational videos that allow users to learn a new language at their own speed [4]. As Chinese becomes more internationalized, there is a surge in demand for Chinese language education [5].…”

Section: Introductionmentioning

confidence: 99%

Language Dissemination Paths and Modes Aided by Computer Technology

Yanghong Wu

2024

jes

View full text Add to dashboard Cite

The expansion of technology and computer science, as well as advancements in language instruction and learning methodologies, has enabled computer-assisted language learning technologies to tackle this challenge. In the field of Chinese learning, a few language learning computerized systems in the country and abroad concentrate mainly on language, grammar acquisition only have one or two assessment indicators as basis of evaluation, that definite functional flaws provide a general assessment to learners' pronunciation. In this manuscript, Language Dissemination Paths and Modes Aided by Computer Technology (LDPM-QICCNN-KOA) are proposed. The input data are collected from Chinese Corpus dataset. Then the data is given into unscented trainable kalman filter for preprocessing the input data. Then the preprocessed data are provided to QICCNN for Language Dissemination. In general, the based Quantum-inspired Complex Convolutional Neural Network doesn’t express adapting optimization approaches to determine optimal parameters to ensure exact identification. Hence, KOA utilized to enhance Quantum-inspired Complex Convolutional Neural Network, which accurately done the Language Dissemination Paths and Modes. The proposed LDPM-QICCNN-KOA method is executed on python. Then performance of proposed technique is analyzed with other existing methods. The proposed technique attains 26.36%, 20.69% and 35.29% higher accuracy; 19.23%, 23.56%, and 33.96% higher F1-Score; 26.28%, 31.26%, and 19.66% higher precision when comparing with the existing methods such as research on network oral English teaching system depend on machine learning (LDPM-DBN), nonlinear network speech recognition structure in deep learning algorithm (LDPM-DNN), research on open oral English scoring system depend on neural network (LDPM-BPNN).

show abstract

“…However, with the addition of authentic images, it will inevitably have a negative impact on the localization performance and can make it difficult for the model to converge. For the second question, some researchers tried to utilize the semantic segmentation models to enhance the localization accuracy of pixel-level forgery, which mainly involve the semantic features [12,13]. Nevertheless, unlike semantic segmentation, image forgery detection focuses more on tampering artifacts [8] rather than image content.…”

Section: Introductionmentioning

confidence: 99%

Image Forgery Detection Using Tamper-Guided Dual Self-Attention Network with Multiresolution Hybrid Feature

Pei

Wei

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Image forgery detection can efficiently capture the difference between the tampered area and the nontampered area. However, existing work usually overemphasizes pixel-level localization, ignoring image-level detection. As a result, false detection for tampered image maybe cause a large number of false positives. To address this problem, we propose an end-to-end fully convolutional neural network. In this framework, multiresolution hybrid features from RGB stream and noise stream are firstly fused to learn visual artifacts and compression inconsistency artifacts, which can efficiently identify the tampered images. Furthermore, a tamper-guided dual self-attention (TDSA) module is designed, which can focus the network’s attention on the tampered areas and segment them from the image by capturing the difference between the tampered area and the nontampered area. Extensive experiments demonstrate that compared to existing schemes, our scheme can simultaneously effectively achieve pixel-level forgery localization and image-level forgery detection while maintaining higher detection accuracy and stronger robustness.

show abstract

A Deep Learning Method for Android Application Classification Using Semantic Features

Cited by 8 publications

References 33 publications

Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review

Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review

Language Dissemination Paths and Modes Aided by Computer Technology

Image Forgery Detection Using Tamper-Guided Dual Self-Attention Network with Multiresolution Hybrid Feature

Contact Info

Product

Resources

About