检索结果-内蒙古大学图书馆

Australian Computer Science Week (ACSW)

作者： Patel, Akash Kumar, Nitesh Handa, Anand Shukla, Sandeep K. IIT Kanpur C3i Ctr Kanpur India

ISBN: (纸本)9798400700057

As the number of smartphone users increases, the attacker's interest in breaching android security also increases. To protect the user from malware attacks and enhance his mobile security, we present AProctor, an android application capable of differentiating between benign and malware applications on the android device. AProctor is a serverless solution. Hence it is a complete on-device solution. Indeed famous anomaly-based detection can protect the user from new and unknown malware, but it has its downsides. Anomaly-based algorithms demand a significant amount of energy and resource, but the platform for which we are developing malware detectors is resource-constrained android phones. So for this, we first implemented a fast and efficient way to extract features in the android device. We collect the dataset from various repositories and categorize them according to their packaging time. We use the feature importance technique to reduce the feature set to build lightweight models. We train our model on the server and deploy it on the device. The detection rate of AProctor is 97% when the training and testing sets are of the same period. Moreover, the detection rate comes to 92% when the test set is of a different period, i.e., for unknown APKs.

关键词： android malware detection malware Analysis Machine learning On-device detection

来源：评论

学校读者我要写书评

暂无评论

Unveiling vulnerabilities in deep learning-based malware detection: Differential privacy driven adversarial attacks

引用

COMPUTERS & SECURITY 2024年 146卷

作者： Taheri, Rahim Shojafar, Mohammad Arabikhan, Farzad Gegov, Alexander Univ Portsmouth Fac Technol Sch Comp Portsmouth England Univ Surrey Inst Commun Syst 5G & 6G Innovat Ctr 5G 6GIC Guildford England

The exponential increase of android malware creates a severe threat, motivating the development of machine learning and especially deep learning-based classifiers to detect and mitigate malicious applications. However, these classifiers are susceptible to adversarial attacks that manipulate input data to deceive the classifier and compromise performance. This paper investigates the vulnerability of deep learning-based android malware classifiers against two adversarial attacks: Data Poisoning with Noise Injection (DP-NI) and Gradient-based Data Poisoning (GDP). In these attacks, we explore the utilization of differential privacy techniques by attackers aiming to compromise the effectiveness of deep learning based android malware classifiers. We propose and evaluate a novel defense mechanism, Differential Privacy-Based Noise Clipping (DP-NC), designed to enhance the robustness of android malware classifiers against these adversarial attacks. By leveraging deep neural networks and adversarial training techniques, DP-NC demonstrates remarkable efficacy in mitigating the impact of both DP-NI and GDP attacks. Through extensive experimentation on three diverse android datasets (Drebin, Contagio, and Genome), we evaluate the performance of DP-NC against proposed adversarial attacks. Our results show that DP-NC significantly reduces the false-positive rate and improves classification accuracy across all datasets and attack scenarios. For instance, our findings on the Drebin dataset reveal a significant decrease in accuracy to 51% and 30% after applying DP-NI and GDP techniques, respectively. However, upon applying the DP-NC defense mechanism, the accuracy in both cases improved to approximately 70%. Furthermore, employing DP-NC defense against DP-NI and GDP attacks leads to a notable reduction in false positive rates by 45.46% and 7.67%, respectively. Similar results have been obtained in two other datasets, Contagio and Genome. These results underscore the effectiveness of

关键词： Adversarial attacks android malware detection Deep learning Differential privacy Gradient perturbation

来源：评论

学校读者我要写书评

暂无评论

Strengthening LLM ecosystem security: Preventing mobile malware from manipulating LLM-based applications

引用

INFORMATION SCIENCES 2024年 681卷

作者： Huang, Lu Xue, Jingfeng Wang, Yong Chen, Junbao Lei, Tianwei Beijing Inst Technol Beijing 100081 Peoples R China

Large language model (LLM) platform vendors have begun to make their models available for developers to build for different use cases. However, the emergence of LLM-based applications may raise security and privacy issues, and even LLM-based applications may be susceptible to malware. To strengthen LLM ecosystem security, it's crucial to develop malware detection algorithms for various platforms. We pay attention to android malware because the android platform is widely used and vulnerable. Existing single feature based-solutions cannot effectively describe applications, and aged models fail to detect new malware as android platform develops and malware evolves. Therefore, existing detection methods are ill-suited for evolved malware that may manipulate LLM-based applications. To tackle the above problems, we design EvolveDroid, an anti-aging android malware detection system. On the one hand, EvolveDroid utilizes different view features to reflect malware behavior from multiple dimensions, and maximizes the advantages of each feature type through feature aggregation. On the other hand, EvolveDroid learns good representation of applications through contrastive learning and generates pseudo labels by measuring the distance between unknown samples and existing samples for model updating. Extensive evaluations show that EvolveDroid outperforms stateof-the-art (sota) solutions in detection performance and slowing model aging.

关键词： LLM security LLM ecosystem android malware detection Contrastive learning Model aging

来源：评论

学校读者我要写书评

暂无评论

AI-powered malware detection with Differential Privacy for zero trust security in Internet of Things networks

引用

AD HOC NETWORKS 2024年 161卷

作者： Nawshin, Faria Unal, Devrim Hammoudeh, Mohammad Suganthan, Ponnuthurai N. Qatar Univ Coll Engn KINDI Comp Res Ctr Doha Qatar Qatar Univ Coll Engn Dept Comp Sci & Engn Doha Qatar King Fahd Univ Petr & Minerals Informat & Comp Sci Dhahran Saudi Arabia

The widespread usage of android-powered devices in the Internet of Things (IoT) makes them susceptible to evolving cybersecurity threats. Most healthcare devices in IoT networks, such as smart watches, smart thermometers, biosensors, and more, are powered by the android operating system, where preserving the privacy of user-sensitive data is of utmost importance. Detecting android malware is thus vital for protecting sensitive information and ensuring the reliability of IoT networks. This article focuses on AI-enabled android malware detection for improving zero trust security in IoT networks, which requires android applications to be verified and authenticated before providing access to network resources. The zero trust security model requires strict identity verification for every entity trying to access resources on a private network, regardless of whether they are inside or outside the network perimeter. Our proposed solution, DP-RFECV-FNN, an innovative approach to android malware detection that employs Differential Privacy (DP) within a Feedforward Neural Network (FNN) designed for IoT networks under the zero trust model. By integrating DP, we ensure the confidentiality of data during the detection process, setting a new standard for privacy in cybersecurity solutions. By combining the strengths of DP and zero trust security with the powerful learning capacity of the FNN, DP-RFECV-FNN demonstrates the ability to identify both known and novel malware types and achieves higher accuracy while maintaining strict privacy controls compared with recent papers. DP-RFECVFNN achieves an accuracy ranging from 97.78% to 99.21% while utilizing static features and 93.49% to 94.36% for dynamic features of android applications to detect whether it is malware or benign. These results are achieved under varying privacy budgets, ranging from epsilon = 0.1 to epsilon = 1.0. Furthermore, our proposed feature selection pipeline enables us to outperform the state-of-the-art by signi

关键词： Privacy-preserving machine learning Zero trust android malware detection malware category classification Differential Privacy Privacy budget

来源：评论

学校读者我要写书评

暂无评论

TraceDroid: Detecting android malware by Trace of Privacy Leakage 17th

TraceDroid: Detecting Android Malware by Trace of Privacy Le...

引用

17th International Conference on Wireless Algorithms, Systems, and Applications (WASA)

作者： Wu, Yueqing Fu, Hao Zhang, Guoming Zhao, Bin Xu, Minghui Zou, Yifei Feng, Xiaotao Hu, Pengfei Shandong Univ Qingdao 266237 Peoples R China Univ Calif Davis Davis CA 95616 USA JD Com Amer Technol Corp Mountain View CA 94043 USA

ISBN: (纸本)9783031192074;9783031192081

Along with the popularity of the android operating system, 98% of mobile malware targets android devices [1], which has become one of the primary source for privacy leakage. Detecting malicious network transmissions in these apps is challenging because the malware hides its behavior and masquerades as benign software to evade detection. In this work, we propose TraceDroid, a framework that can automatically trace abnormally sensitive network transmissions to detect the malware. By leveraging the static and dynamic analysis, the sensitive informations can be firstly inferred from the call graph, and then, the sensitive transmissions can be detected by analyzing the network traffic per transfer and sensitive information with a machine learning classifier. We validate TraceDroid on 1444 malware and 700 benign applications. And our experiments show that TraceDroid can detect 3433 sensitive connections across 2144 apps with an accuracy of 94%.

关键词： android malware detection Static analysis Dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

android malware Classification: Updating Features Through Incremental Learning Approach(UFILA) 24

Android Malware Classification: Updating Features Through In...

引用

24th International Conference on Advanced Communication Technology (ICACT) - Artificial Intelligence Technologies toward Cybersecurity

作者： Sawadogo, Zakaria Mendy, Gervais Dembelle, Jean Marie Ouya, Samuel Gaston Berger Univ Lab LANI St Louis Senegal Univ Cheikh Anta Diop Dakar Lab LITA Dakar Senegal

ISBN: (纸本)9791188428090

exponential growth of the use of connected objects, in particular of smartphones, is the consequence of the digitization of services. All types of applications, from the least critical to the most critical are available on mobile devices through mobile applications. The daily penetration of mobile applications in widely used devices brings certain threats. We find in the software repositories malwares and good application at the same time, which is a major cybersecurity problem. To resolve this problem, machine learning approaches have been proposed in the literature for the detection of malware in general and android malicious applications in particular. Obfuscation techniques are used by developers to hide malicious applications that implies the need to update android malware detection models. But many approaches in the literature are more focus on data than features. Hence our contribution is an incremental learning approach capable of detecting android malware. We propose through UFILA approach an updating of features for the detection and classification of android malware by adding new features. We evaluated 13 classification algorithms and chose four most efficient algorithms to implement our approach. The results obtained by our approach surpass several malware detection approaches in the literature. The values of the metrics obtained respectively by the Accuracy, the precision, the recall and an F1-Score are 99%, 99%,98.6 %98%.

关键词： android malware classification classification algorithm incremental learning android malware detection machine learning cyber-security

来源：评论

学校读者我要写书评

暂无评论

android malware classification using convolutional neural network and LSTM

引用

JOURNAL OF COMPUTER VIROLOGY AND HACKING TECHNIQUES 2021年第4期17卷 307-318页

作者： Hosseini, Soodeh Nezhad, Ali Emamali Seilani, Hossein Shahid Bahonar Univ Kerman Fac Math & Comp Dept Comp Sci Kerman Iran Bahmanyar Univ Kerman Sch Comp Engn Kerman Iran

Hand phone devices are the latest technological developments of the 20th century. There is an increasing number of fishing, sniffing and other kinds of attacks in this field of technology. Although signature-based methods are usable, they are not very reliable when faced with new kinds of malwares and they are neither accurate nor enough. Furthermore, signature-based methods cannot efficiently detect rapid malware behavior changes. Our classification process consists of not only analyzing of the source code by using Jadx but also analyzing applications and extracting useful features. Two kinds of analyses are used which are called static and dynamic. We concentrate on android malware classification using Call-Graph and by moreover generating Call-Graphs for both *** and *** files which have not been worked before. The proposed method for classification is CNN-LSTM. Since this method is a reasonable choice to learn complex and sequential features, it benefits from both convolutional neural network and long short-term memory which is a type of recurrent neural network. In this method a Sequential Neural Network is designed to do sequence classification as well as conduct a set of experiments on malware detection. In conclusion, CNN-LSTM is compared with several classification methods like Convolutional Neural Network (CNN), Support Vector Machine (SVM), Naive Bayes, Random Forest, and other methods. Obtained results show that, our method is more effective, efficient, and reliable than others even by using the same hardware and dataset.

关键词： android malware detection Call Graph Convolutional Neural Network Long Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

Breaking the structure of MaMaDroid

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期228卷

作者： Berger, Harel Dvir, Amit Mariconti, Enrico Hajaj, Chen Georgetown Univ Comp Sci Dept 37th & O St NW Washington DC 20057 USA Ariel Univ Ariel Cyber Innovat Ctr Comp Sci Dept 65 Ramat HaGolan st IL-4076414 Ariel Israel UCL Jill Dando Inst Dept Secur & Crime Sci Gower St London WC1E 6BT England Data Sci & Artificial Intelligence Res Ctr Dept Ind Engn & Management 65 Ramat HaGolan st IL-4076414 Ariel Israel

android malware is a continuously expanding threat to billions of mobile users around the globe. detection systems are updated constantly to address these threats. However, a backlash takes the form of evasion attacks, in which an adversary changes malicious samples in the wild such that they will be misclassified as benign. This paper comprehensively inspects a well-known android malware detection system, MaMaDroid, which analyzes the control flow graph of the application. Changes in the portion of benign samples in the training set are considered to reveal their effect on the resulting classifier. These changes in the ratio between benign and malicious samples have a clear effect on each of the models, resulting in a decrease of more than 40% in their detection rate, model confidence, and reliability. Moreover, adopted Machine Learning models were implemented as well, including 5-NN, Decision Tree, and Adaboost. Exploration of the six models showed a typical behavior in different cases, of tree-based models and distance-based models. Moreover, three novel attacks that manipulate the Control Flow Graph (CFG) are described for each of the targeted models. The attacks decrease the detection rate of most models to less than 10%, with regards to different ratios of benign to malicious apps. As a result, a new version of MaMaDroid is engineered, which fuses the CFG of the app and static analysis of features of the app. This improved model is proven to be robust against evasion attacks targeting CFG-based models and static analysis models, achieving a detection rate of similar to 80%.

关键词： Machine learning Evasion attacks android malware detection

来源：评论

学校读者我要写书评

暂无评论

Towards a fair comparison and realistic evaluation framework of android malware detectors based on static analysis and machine learning

引用

COMPUTERS & SECURITY 2023年 124卷

作者： Molina-Coronado, Borja Mori, Usue Mendiburu, Alexander Miguel-Alonso, Jose Univ Basque Country UPV EHU Dept Comp Architecture & Technol Ps Manuel Lardizabal 1 Donostia San Sebastian 20018 Gipuzkoa Spain Univ Basque Country UPV EHU Dept Comp Sci & Artificial Intelligence Ps Manuel Lardizabal 1 Donostia San Sebastian 20018 Gipuzkoa Spain

As in other cybersecurity areas, machine learning (ML) techniques have emerged as a promising solution to detect android malware. In this sense, many proposals employing a variety of algorithms and feature sets have been presented to date, often reporting impresive detection performances. However, the lack of reproducibility and the absence of a standard evaluation framework make these proposals difficult to compare. In this paper, we perform an analysis of 10 influential research works on android malware detection using a common evaluation framework. We have identified five factors that, if not taken into account when creating datasets and designing detectors, significantly affect the trained ML models and their performances. In particular, we analyze the effect of (1) the presence of duplicated samples, (2) label (goodware/greyware/malware) attribution, (3) class imbalance, (4) the presence of apps that use evasion techniques and, (5) the evolution of apps. Based on this extensive experimentation, we conclude that the studied ML-based detectors have been evaluated optimistically, which justifies the good published results. Our findings also highlight that it is imperative to generate realistic experimental scenarios, taking into account the aforementioned factors, to foster the rise of better ML-based android malware detection solutions. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： android malware detection Machine learning Mobile security Experimental analysis Static analysis

来源：评论

学校读者我要写书评

暂无评论

MulAV: Multilevel and Explainable detection of android malware with Data Fusion 18th

MulAV: Multilevel and Explainable Detection of Android Malwa...

引用

18th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Li, Qun Chen, Zhenxiang Yan, Qiben Wang, Shanshan Ma, Kun Shi, Yuliang Cui, Lizhen Univ Jinan Sch Informat Sci & Engn Jinan 250022 Shandong Peoples R China Shandong Prov Key Lab Network Based Intelligent C Jinan 250022 Shandong Peoples R China Univ Nebraska Lincoln NE USA Shandong Univ Jinan 250101 Shandong Peoples R China

ISBN: (纸本)9783030050634;9783030050627

With the popularization of smartphones, the number of mobile applications has grown substantially. However, many malware are emerging and thus pose a serious threat to the user's mobile phones. malware detection has become a public concern that requires urgent resolution. In this paper, we propose MulAV, a multilevel and explainable detection method with data fusion. Our method obtain information from multiple levels (the APP source code, network traffic, and geospatial information) and combine it with machine learning method to train a model which can identify mobile malware with high accuracy and few false alarms. Experimental result shows that MulAV outperforms other anti-virus scanners and methods and achieves a detection rate of 97.8% with 0.4% false alarms. Furthermore, for the benefit of users, MulAV displays the explanation for each detection, thus revealing relevant properties of the detected malware.

关键词： android malware detection Data fusion Multilevel Result explanation

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：