SMS Observer: A dynamic mechanism to analyze the behavior of SMS-based malware

Wang, Chun Yi; You, Chi Yu; Hsu, Fu-Hau; Lee, Chia-Hao; Liu, Che Hao; Zhuang, YungYu

doi:10.1016/j.jpdc.2021.05.004

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic analysis involves executing malware samples in a controlled environment to observe their behavior during runtime. An effective method used to investigate malware is by analyzing the program's behavior during execution [16], [17]. This approach, also known as behavioral analysis, involves observing and collecting information from the operating system including API call sequence analysis, system call monitoring, network traffic analysis, sandboxing, and memory behavior analysis.…”

Section: B Dynamic Analysismentioning

confidence: 99%

“…Trainable parameters represent the bulkiness of the architecture. True Positive Rate (TPR) measures the proportion of positive instances correctly classified as positive by a model, presented in equation (17). While False Positive Rate (FPR) quantifies the ratio of negative instances incorrectly classified as positive given in equation (18).…”

Section: B Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification

Puneeth,

Lal,

Pratap Singh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Malware analysis and detection are still essential for maintaining the security of networks and computer systems, even as the threat landscape shifts. Traditional approaches are insufficient to keep pace with the rapidly evolving nature of malware. Artificial Intelligence (AI) assumes a significant role in propelling its design to unprecedented levels. Various Machine Learning (ML) based malware detection systems have been developed to combat the ever-changing characteristics of malware. Consequently, there is a growing interest in exploring advanced techniques that leverage the power of Deep Learning (DL) to effectively analyze and detect malicious software. DL models demonstrate enhanced capabilities for analyzing extensive sequences of system calls. This paper proposes a Robust Malware Detection Network (RMDNet) for effective malware detection and classification. The proposed RMDNet model branches the input and performs depth-wise convolution and concatenation operations. The experimental results of the proposed RMDNet and existing DL models are evaluated on 48240 malware and binary visualization image dataset with RGB format. Also on the multi-class malimg and dumpware-10 datasets with grayscale format. The experimental results on each of these datasets demonstrate that the proposed RMDNet model can effectively and accurately categorize malware, outperforming the most recent benchmark DL algorithms.

show abstract

Section: B Dynamic Analysismentioning

confidence: 99%

Section: B Evaluation Metricsmentioning

confidence: 99%

RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification

Puneeth,

Lal,

Pratap Singh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…where We chose two images which a SSIM value between 0.6 and 0.7, then combined the two malware images with an 8:2 ratio to generate a new image as a variant. The combined image of images x and y is calculated as Equation (5).…”

Section: Ssim(x Y)mentioning

confidence: 99%

“…Key features including permissions, intent, API calls, and system calls are collected to train classifiers to generate models for identifying samples in the test dataset 4 . Some approaches, such as dynamic analysis 5 and static analysis, 6 are frequently used to extract the features of malware. However, dynamic analysis needs to execute the malware in the virtual environment to obtain the behaviors of malware so that it may take lots of time and resources 7 .…”

Section: Introductionmentioning

confidence: 99%

Malware detection method based on image analysis and generative adversarial networks

Liu

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Malware detection is indispensable to cybersecurity. However, with the advent of new malware variants and scenarios with few and imbalanced samples, malware detection for various complex scenarios has been a very challenging problem. In this article, we propose a malware detection method based on image analysis and generative adversarial networks, named MadInG, which can improve the accuracy of malware detection for insufficient samples, sample imbalance, and new variants scenarios. Specifically, we first generate fixed‐size grayscale images of malware to reduce the workload of feature engineering or the involvement of domain expert knowledge on malware detection. Then we introduce auxiliary classifier generative adversarial networks into malware detection to enhance the generalization ability of the detector. Finally, we construct a variety of malware scenarios and compare our proposed method with existing popular detection methods. Extensive experimental results demonstrate that our method achieves high accuracy and well balance in malware detection for different scenarios, especially, the detection rate of malware variants reaches 99.5%.

show abstract

“…For that, the proposed solution used here is to command the operation mode of the device with SMS messages to make the device in wake up/sleep mode. In this case, to manage the sleep mode using SMS messaging, we based on Nexmo REST API getaway [27]. This one allows us to send and receive text messages to users around the globe through simple RESTful APIs.…”

mentioning

confidence: 99%

A novel autonomous remote system applied in agriculture using transmission control protocol

Deroussi

Madi

Alihamidi

et al. 2022

IJRES

View full text Add to dashboard Cite

<span lang="EN-US">An internet of things (IoT) irrigation system is challenged by several issues, such as cost, energy consumption, and data storage. This paper proposes a novel energy-efficient, cost-effective IoT system called "NewAgriCom" to monitor agricultural field water flow. NewAgriCom works with an embedded energy harvesting system, is an autonomous remote supervisory control and data acquisition (SCADA) based on a general packet radio service (GPRS) cellular network that effectively communicates irrigation field data to the Node.js server using SIM808 EVBV3.2 modem. In javascript object notation (JSON) format, data is transmitted over the hypertext transfer protocol (HTTP) protocol to the MySQL database. Then data are transferred to the proposed IoT platform, which gives us a hand to control actuators, visualise, store and download the data. NewAgriCom can significantly reduce water consumption. It can set a schedule to control water automatically at specific times in various modes, including normal, light, and deep sleep modes. It regularly provides the location, time, signal strength, and the state of actuators with the identifier of every device remotely on the IoT Platform.</span><p> </p>

show abstract

SMS Observer: A dynamic mechanism to analyze the behavior of SMS-based malware

Cited by 7 publications

References 15 publications

RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification

RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification

Malware detection method based on image analysis and generative adversarial networks

A novel autonomous remote system applied in agriculture using transmission control protocol

Contact Info

Product

Resources

About