M4D: A Malware Detection Method Using Multimodal Features

2019 ◽  
pp. 228-238
Author(s):  
Yusheng Dai ◽  
Hui Li ◽  
Xing Rong ◽  
Yahong Li ◽  
Min Zheng
Keyword(s):  
Detection Method ◽  
Malware Detection ◽  
Multimodal Features

scholarly journals SUIP: An Android malware detection method based on data flow features

2021 ◽  
Vol 1812 (1) ◽  
pp. 012010
Author(s):  
X R Chen ◽  
S S Shi ◽  
C L Xie ◽  
Z Yang ◽  
Y J Guo ◽  
...  
Keyword(s):  
Data Flow ◽  
Detection Method ◽  
Malware Detection ◽  
Android Malware ◽  
Android Malware Detection ◽  
Flow Features

scholarly journals Permission Sensitivity-Based Malicious Application Detection for Android

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yubo Song ◽  
Yijin Geng ◽  
Junbo Wang ◽  
Shang Gao ◽  
Wei Shi
Keyword(s):  
Detection Method ◽  
Malware Detection ◽  
Feature Selection Method ◽  
Machine Learning Algorithms ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Android Malware ◽  
Android Malware Detection ◽  
Private Data ◽  
Weight Allocation

Since a growing number of malicious applications attempt to steal users’ private data by illegally invoking permissions, application stores have carried out many malware detection methods based on application permissions. However, most of them ignore specific permission combinations and application categories that affect the detection accuracy. The features they extracted are neither representative enough to distinguish benign and malicious applications. For these problems, an Android malware detection method based on permission sensitivity is proposed. First, for each kind of application categories, the permission features and permission combination features are extracted. The sensitive permission feature set corresponding to each category label is then obtained by the feature selection method based on permission sensitivity. In the following step, the permission call situation of the application to be detected is compared with the sensitive permission feature set, and the weight allocation method is used to quantify this information into numerical features. In the proposed method of malicious application detection, three machine-learning algorithms are selected to construct the classifier model and optimize the parameters. Compared with traditional methods, the proposed method consumed 60.94% less time while still achieving high accuracy of up to 92.17%.

scholarly journals An API Semantics-Aware Malware Detection Method Based on Deep Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Xin Ma ◽  
Shize Guo ◽  
Wei Bai ◽  
Jun Chen ◽  
Shiming Xia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Detection Method ◽  
Malware Detection ◽  
Poor Performance ◽  
Detection Methods ◽  
Interference Detection ◽  
Machine Learning Method ◽  
Accuracy Rate ◽  
Malware Classification ◽  
Self Protection

The explosive growth of malware variants poses a continuously and deeply evolving challenge to information security. Traditional malware detection methods require a lot of manpower. However, machine learning has played an important role on malware classification and detection, and it is easily spoofed by malware disguising to be benign software by employing self-protection techniques, which leads to poor performance for existing techniques based on the machine learning method. In this paper, we analyze the local maliciousness about malware and implement an anti-interference detection framework based on API fragments, which uses the LSTM model to classify API fragments and employs ensemble learning to determine the final result of the entire API sequence. We present our experimental results on Ali-Tianchi contest API databases. By comparing with the experiments of some common methods, it is proved that our method based on local maliciousness has better performance, which is a higher accuracy rate of 0.9734.

A Dynamic Malware Detection Approach by Mining the Frequency of API Calls

2014 ◽  
Vol 519-520 ◽  
pp. 309-312 ◽  
Author(s):  
Jin Rong Bai ◽  
Zhen Zhou An ◽  
Guo Zhong Zou ◽  
Shi Guang Mu
Keyword(s):  
Detection Rate ◽  
Detection Method ◽  
Malware Detection ◽  
Experimental Results ◽  
Detection Approach ◽  
Dynamic Detection

Dynamic detection method based on software behavior is an efficient and effective way for anti-virus technology. Malware and benign executable differ mainly in the implementation of some special behavior to propagation and destruction. A program's execution flow is essentially equivalent to the stream of API calls. Analyzing the API calls frequency from six kinds of behaviors in the same time has the very well differentiate between malicious and benign executables. This paper proposed a dynamic malware detection approach by mining the frequency of sensitive native API calls and described experiments conducted against recent Win32 malware. Experimental results indicate that the detection rate of proposed method is 98% and the value of the AUC is 0.981. Furthermore, proposed method can identify known and unknown malware.

Sign in / Sign up

Export Citation Format

Share Document