Open Access Open Access  Restricted Access Subscription Access

Trojan Malware Detection Using Steganography, Deep Learning and Machine Learning Concepts

Hari Krishnan Anil Jameni, Lekshmi Anil, Navya Asok, Jasim S, Mruthula N R

Abstract


Take into account an attack scenario where a payload is encoded into a DNA sequence in order to activate Trojan malware implanted in a software tool used in the sequencing pipeline. This will enable the perpetrators to take control over the resources used in that pipeline during sequence analysis. The scenario examined in the research is predicated on offenders submitting samples of synthetically created DNA that have been digitally encoded with the IP address and port number of the hacker’s machine. This article utilizes AI and Profound Learning advancements to shield DNA sequencing against such Bio-Digital assaults. The situation considered in the paper depends on culprits submitting artificially designed DNA tests that contain carefully encoded IP address and port number of the culprit's machine in the DNA. This system passes on space for a few guilty parties to lay out associations and assume control over the DNA sequencing pipeline. The guilty parties can sidestep ID by encoding the location to boost similarity with genuine DNAs, as we recently illustrated, to hide the information. Conversely, we show in this study how AI can be used to successfully distinguish and recognize the trigger encoded information to protect a DNA sequencing pipeline from trojan assaults. The explanation AI is liked over Profound Learning is on the grounds that it lessens the intricacy of the code and cycle at the expense of a slight decrease in the precision.  On the off chance that Profound Learning has a precision of 98.7%, the AI approach can furnish an exactness of 98.1% with a significant decrease in the task intricacy. Indeed, even in the wake of applying discontinuity encryption and steganography to the encoded trigger information, the recommended approach is anticipated to give up to high exactness in location in such an exceptional Trojan assault situation.


Full Text:

PDF

References


Ney, P. et al. Computer security, privacy, and DNA sequencing: Compromising computers with synthesized DNA, privacy leaks, and more. USENIX Security 17, 2017.

Islam, M. S. et al. “Genetic similarity of biological samples to counter biohacking of DNA sequencing functionality.” Scientific Reports vol. 9 (2019)

Malathi Pa , Manoaj Ma ,Manoj Ra , Vaikunth Raghavana ,Vinodhini R Ea. “Highly Improved DNA Based Steganography.”

Liu, J. et al. “DNA-Based Authentication and Encryption Schemes for Secure Data Storage.” IEEE Transactions on Information Forensics and Security, 2019.

Santoso, K.N. “Sector-based DNA Information Hiding Method.” Journal of Bioinformatics and Computational Biology, 2023.

“Duplication-Correcting Codes for Data Storage in the DNA of Living Organisms.” Siddharth Jain, Student Member, IEEE, Farzad Farnoud (Hassanzadeh), Member, IEEE, Moshe Schwartz, Senior Member, IEEE, and Jehoshua Bruck, Fellow, IEEE

“DeepMalware: A Deep Learning Approach for Malware Detection Using Long Short-Term Memory.” Saxeena, M. et al. International Journal of Computer Science and Information Security, 2019

”Bio-Cybersecurity: Remote DNA Injection Attack on a Sequencing Workflow System.” Gao, A. et al. Published in: IEEE

Huang, W., & Liu, Y. (2019). A Hybrid Deep Learning Approach for Trojan Malware Detection. In Proceedings of the 16th IEEE International Conference on Networking, Sensing and Control (ICNSC) (pp. 1-6). IEEE.

Li, Z., Xue, Y., & Sun, B. (2018). A Novel Approach for Detecting Trojan Malware Based on Convolutional Neural Networks. In Proceedings of the 2nd International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) (pp. 1-5). IEEE.


Refbacks

  • There are currently no refbacks.