JPEG Vigilant : AI-Powered Malware Image Detection
Keywords:
Machine learning, malware, detection, JPEG, image, features.Abstract
Cyberattacks against people, companies, and organizations have risen in recent years.In order to conduct an attack, cybercriminals are constantly searching for efficient channels to spread malware to targets. Millions of people use photos every day, and the majority of consumers believe that they are safe to use. However, some types of images may contain malicious payloads that carry out dangerous functions. Due in large part to its lossy compression, JPEG is the most widely used image for mat.In this study, we introduce JPEGVigilant, the first machine learning-based method designed exclusively for the quick and accurate identification of unknown malicious JPEG images. In order to distinguish between benign and malicious JPEG images, JPEGVigilant statically derives 10 straightforward yet discriminative properties from the JPEG LE structure.
References
- T. Kumar, S. Sharma, Goel, S. Chaudhary, and P. Jain. A Novel Machine Learning Approach for Malware Detection. Accessed: 2019. [Online]. Available:https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3383953
- S. Sharma, C. R. Krishna, and S. K. Sahay, ``Detection of advanced malware by machine learning techniques,'' in Soft Computing: Theories and Applications. Singapore: Springer, 2019, pp. 333342.
- N. Nissim, R. Moskovitch, L. Rokach, and Y. Elovici, ``Novel active learning methods for enhanced PC malware detection in windows OS,'‘ Expert Syst. Appl., vol. 41, no. 13, pp. 58435857, Oct. 2014.
- D. Nahmias, A. Cohen, N. Nissim, and Y. Elovici, ``TrustSign: Trusted malware signature generation in private clouds using deep feature transfer learning,'' in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Jul. 2019,pp. 18.
- N. Nissim, A. Cohen, R. Moskovitch, A. Shabtai, M. Edri, O. Bar-Ad,and Y. Elovici, ``Keeping pace with the creation of new malicious PDF les using an active-learning based detection framework,'' Secur. Inform., vol. 5, p. 1, Dec. 2016.
- T. Denemark, P. Bas, and J. Fridrich, ``Natural steganography in JPEG compressed images,'' Electron. Imag., vol. 2018, no. 7, pp. 316-1316-10, Jan. 2018.
- D. Ucci, L. Aniello, and R. Baldoni, ``Survey of machine learning techniques for malware analysis,'' Comput. Secur., vol. 81, pp. 123147,Mar. 2019.
- O. Or-Meir, N. Nissim, Y. Elovici, and L. Rokach, ``Dynamic malware analysis in the modern eraA state of the art survey,'' CSURACMComput. Surv., vol. 52, no. 5, pp. 148, Sep. 2019.
- N. Nissim, A. Cohen, J. Wu, A. Lanzi, L. Rokach, Y. Elovici, and L. Giles, ``Sec-lib: Protecting scholarly digital libraries from infected papers using active machine learning framework,'' IEEE Access, vol. 7,pp. 110050110073, 2019.
- Y.-S. Jeong, J. Woo, and A. R. Kang, ``Malware detection on byte streams of PDF les using convolutional neural networks,'' Secur. Commun. Netw., vol. 2019, pp. 19, Apr. 2019.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.