1,092 Hits in 5.7 sec

Multichannel Based IoT Malware Detection System Using System Calls and Opcode Sequences

Shobana Manoharan, Poonkuzhali Sugumaran, Kishore Kumar
2022 ˜The œinternational Arab journal of information technology  
The real-time Internet of Things (IoT) malware samples were collected from the IoT honeyPot (IOTPOT), which emulates different CPU architectures of IoT devices.  ...  These extracted system calls and opcode sequences of elf files were discriminated against using two more deep learning algorithms along with multichannel CNN, namely Recurrent Neural Network (RNN) and  ...  An et al [5] suggested a malware detection system for the Amazon Alexa Echo using system calls from IoT malware.  ... 
doi:10.34028/iajit/19/2/13 fatcat:wfumduxi2rexjk4atyu2ptkvq4

Android Malware Detection via Graph Representation Learning

Pengbin Feng, Jianfeng Ma, Teng Li, Xindi Ma, Ning Xi, Di Lu, Raul Montoliu
2021 Mobile Information Systems  
Then, we use the graph neural network to generate a vector representation of the application, and then malware detection is performed on this representation space.  ...  Particularly, we construct approximate call graphs from function invocation relationships within an Android application to represent this application and further extract intrafunction attributes, including  ...  approximate call graph to perform effective malware detection.  ... 
doi:10.1155/2021/5538841 fatcat:o4beznwd4zadvcqfqubbwgalmy

Comprehensive Analysis of IoT Malware Evasion Techniques

A. Al-Marghilani
2021 Engineering, Technology & Applied Science Research  
Many security researchers have studied the IoT malware detection domain. Many studies proposed the static or dynamic analysis on IoT malware detection.  ...  Malware detection in Internet of Things (IoT) devices is a great challenge, as these devices lack certain characteristics such as homogeneity and security.  ...  [31] Non-graph and graph-based malware detection methods. Two groups of malware detection methods were used: non-graph and graph-based methods.  ... 
doi:10.48084/etasr.4296 fatcat:hyfkdspwizce3cyeu6erygpqai

A Deep Learning-based Fine-grained Hierarchical Learning Approach for Robust Malware Classification [article]

Ahmed Abusnaina, Mohammed Abuhamad, Hisham Alasmary, Afsah Anwar, Rhongho Jang, Saeed Salem, DaeHun Nyang, David Mohaisen
2020 arXiv   pre-print
To do so, examine the performance of the state-of-the-art methods against adversarial IoT software crafted using the graph embedding and augmentation techniques.  ...  Upon optimization and with small perturbation, by use of SGEA, all the IoT malware samples are misclassified as benign.  ...  [51] proposed a graph-based detection system that uses a quantitative data flow graphs generated from the system calls, and use the graph node properties, i.e., centrality metric, as a feature vector  ... 
arXiv:2005.07145v2 fatcat:vsiin3udfjfd7acelbdh5vkhiu

Dynamic Analysis for IoT Malware Detection with Convolution Neural Network model

Jueun Jeon, Jong Hyuk Park, Young-Sik Jeong
2020 IEEE Access  
The DAIMD scheme learns IoT malware using the convolution neural network (CNN) model and analyzes IoT malware dynamically in nested cloud environment.  ...  INDEX TERMS Cloud-based malware detection, convolution neural network, dynamic analysis, IoT malware, malware detection.  ...  In addition, various actions in memory, network, process, system call, and virtual file system are extracted to detect malware that perform malicious actions on embedded Linux-based IoT devices.  ... 
doi:10.1109/access.2020.2995887 fatcat:sjch2uh54ja2xapedtkwddwgiq

A Survey on Cross-Architectural IoT Malware Threat Hunting

Anandharaju Durai Raju, Ibrahim AbuAlhaol, Ronnie Salvador Giagone, Yang Zhou, Huang Shengqiang.
2021 IEEE Access  
This study aims at providing a comprehensive survey on the latest developments in cross-architectural IoT malware detection and classification approaches.  ...  We further provide more insights on the practical challenges involved in cross-architectural IoT malware threat hunting and discuss various avenues to instill potential future research.  ...  The PSI-Graph extraction is done as a simplified version of the function call graph (FCG) using only the functions that contain PSI characters with lengths more than or equal to three.  ... 
doi:10.1109/access.2021.3091427 fatcat:tsfno6qdirhbdasj3fzrqqqzm4

Malware Detection and Classification in IoT Network using ANN

Ayesha Jamal, Muhammad Faisal Hayat, Muhammad Nasir
2022 Mehran University Research Journal of Engineering and Technology  
In this paper, we have explored the potential of neural networks for detection and classification of malware using IoT network dataset comprising of total 4,61,043 records with 3,00,000 as benign while  ...  With the proposed methodology, malware is detected with an accuracy of 94.17% while classified with 97.08% accuracy  ...  Function call graphs were created using these samples. Further PSI graphs were created using functions that were close to IoT botnets.  ... 
doi:10.22581/muet1982.2201.08 doaj:0bfd1c088ebb4199a37dd4855d001439 fatcat:x7bvatk7azbcvgon7zzlehntv4

HawkEye: Cross-Platform Malware Detection with Representation Learning on Graphs

Peng Xu, Youyi Zhang, Claudia Eckert, Apostolis Zarras
2021 Zenodo  
In more detail, HawkEye utilizes a graph neural network to convert the control flow graphs of executable to vectors with the trainable instruction embedding and then uses a machine-learning-based classifier  ...  to create a malware detection system.  ...  Related Work MalConv [10] Adagio [4] implements a kernel-hashing-based malware detection system on the function call graph.  ... 
doi:10.5281/zenodo.5750058 fatcat:3j42h4lkojfldjz2tmerqt5ixy

Cognitive and Scalable Technique for Securing IoT Networks Against Malware Epidemics

P D Sai Manoj, Xiaojie Guo, Hossein Sayadi, Cameron Nowzari, Avesta Sasan, Setareh Rafatirad, Liang Zhao, Houman Homayoun
2020 IEEE Access  
It exploits perf_event_open function call in the background to measure multiple events simultaneously.  ...  for runtime malware detection on IoT devices.  ... 
doi:10.1109/access.2020.3011919 fatcat:pdibd3722nay7obxkkomkiy64u

A Novel Framework to Classify Malware in MIPS Architecture-Based IoT Devices

Tran Nghi Phu, Kien Hoang Dang, Dung Ngo Quoc, Nguyen Tho Dai, Nguyen Ngoc Binh
2019 Security and Communication Networks  
IoT devices use the MIPS architecture with a large proportion running on embedded Linux operating systems, but the automatic analysis of IoT malware has not been resolved.  ...  We proposed a framework to classify malware in IoT devices by using MIPS-based system behavior (system call—syscall) obtained from our F-Sandbox passive process and machine learning techniques.  ...  Deep4-MalDroid [15] extracted the Linux kernel system calls from the executing apps on Android, generates a weighted directed graph, and then applies a deep learning framework resting on the graph-based  ... 
doi:10.1155/2019/4073940 fatcat:llefjvtxc5be3h4yc5vemkfcga

Robust Malware Detection for Internet Of (Battlefield) Things Devices Using Deep Eigenspace Learning

Amin Azmoodeh, Ali Dehghantanha, Kim-Kwang Raymond Choo
2018 IEEE Transactions on Sustainable Computing  
A common attack vector is the use of malware.  ...  Lastly, we make available our malware sample on Github, which hopefully will benefit future research efforts (e.g. for evaluation of proposed malware detection approaches).  ...  ACKNOWLEDGMENTS We thank VirusTotal for providing us a private API key to access their data for constructing our dataset.  ... 
doi:10.1109/tsusc.2018.2809665 dblp:journals/tsusc/AzmoodehDC19 fatcat:wo5ppc7j6nc7jhzfplivt7kxii

Static Feature Selection for IoT Malware Detection

Nguyen Ngoc Toan, Luong The Dung, Dang Quang Thang
2022 Journal of Science and Technology on Information security  
IoT malware detection based on opcode sequence features.  ...  Therefore, it is necessary to come up with more efficient approaches to IoT malware detection with machine learning models that can be used in solutions using limited resources.  ...  With static features, common forms have been used include strings [13] , bytes n-gram [14] , opcode [15] , function call graph [16] , entropy-based [17] , etc.  ... 
doi:10.54654/isj.v1i15.844 fatcat:gunra42245hwhfwt3suiftyjhy

Multi-relational Instruction Association Graph for Cross-architecture Binary Similarity Comparison [article]

Qige Song, Yongzheng Zhang, Shuhao Li
2022 arXiv   pre-print
Furthermore, evaluations on a large-scale real-world IoT malware reuse function collection show that our approach is valuable for identifying malware propagated on IoT devices of various architectures.  ...  However, instruction embeddings pre-trained on external code corpus are not universal in diverse real-world applications.  ...  Furthermore, our approach can achieve effective cross-architecture reuse function detection on a large-scale IoT malware dataset collected from the real-world network environment, which is meaningful for  ... 
arXiv:2206.12236v2 fatcat:nt24bnvqg5epppqpkrp2zfrgvi

IDAPro for IoT Malware analysis?

Sri Shaila G, Ahmad Darki, Michalis Faloutsos, Nael B. Abu-Ghazaleh, Manu Sridharan
2019 USENIX Security Symposium  
Defending against the threat of IoT malware will require new techniques and tools.  ...  A key question is whether PC-oriented disassemblers can be effective on IoT malware, given the difference in the malware programs and the processors that support them.  ...  Disassemblers in malware analysis. Several efforts use disassemblers in analyzing the malware structure like call graphs [15] . These studies use disassemblers for malware classification.  ... 
dblp:conf/uss/GDFAS19 fatcat:hnl2vwta6fcxdb5rkn6qbeuyxy

An Efficient Approach to Detect and Classify IoT Malware Based On Byte Sequences from Executable Files

Tzu-Ling Wan, Tao Ban, Shin-Ming Cheng, Yen-Ting Lee, Bo Sun, Ryoichi Isawa, Takeshi Takahashi, Daisuke Inoue
2020 IEEE Open Journal of the Computer Society  
However, current analysis approaches based on opcode or call-graph usually do not work well with the diversity in CPU architectures and are often resource demanding.  ...  In this paper, we propose an efficient scheme to detect and classify IoT malware programs leveraging machine learning methods.  ...  [23] focused on the detection of IoT botnets by using Printable String Information (PSI) -graph as the main feature for the learning.  ... 
doi:10.1109/ojcs.2020.3033974 fatcat:5b55cl3qcvbrdp2hiayqbqkk3y
« Previous Showing results 1 — 15 out of 1,092 results