Abstract
The explosion of IoT gadgets which be able to more effortlessly conceded than PCs has prompted an expansion in the existence of IoT-dependent botnet attacks. So as to alleviate this newfangled danger there remains a necessity to grow innovative techniques designed for identifying attacks propelled from conceded IoT gadgets in addition to distinguish among hour as well as millisecond elongated IoT-dependent attacks. Now we suggest and experimentally estimate a Deep Nonlinear Regression Least Squares Polynomial Fit to recognize peculiar system traffic originating as of conceded IoT gadgets. On the way to estimate our strategy, we contaminated 9 business IoT gadgets in our lab through 2 of the most generally acknowledged IoT-dependent botnets, Mirai and BASHLITE. Our estimated outcomes showed our suggested strategy's capacity to precisely and rapidly recognize the attacks as they were being propelled from the conceded IoT gadgets which remained a piece of a botnet. The tests show a truly accuracy 98.75%.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Arabo A, Pranggono B (2013) Mobile malware and smart device security: Trends, challenges and solutions. In 2013 19th International Conference on Control Systems and Computer Science pp 526–531
Bianco LJ (2016) The inherent weaknesses in industrial control systems devices; hacking and defending SCADA systems (Doctoral dissertation, Utica College)
Chen Y (2019) Comment on the work of Zhang et al. (2017, Journal of Inequalities and Applications). J Inequal Appl 2019:186. https://doi.org/10.1186/s13660-019-2142-3
D’Angelo G, Palmieri F, Rampone S (2019) Detecting unfair recommendations in trust-based pervasive environments. Inf Sci 486:31–51
D’Angelo G, Ficco M, Palmieri F (2020) Malware detection in mobile environments based on Autoencoders and API-images. J Parallel and Distrib Comput 137:26–33
HaddadPajouh H, Dehghantanha A, Khayami R, Choo KKR (2018) A deep Recurrent neural network based approach for internet of things malware threat hunting. Future Gener Comput Syst 85:88–96
Hinton GE, Zemel RS (1994) Autoencoders, minimum description length, and helmholtz free energy. In: Cowan JD, Tesauro G, Alspector J (eds) Advances in neural information processing systems 6. Morgan Kaufmann, San Mateo, CA
Macías-Escrivá FD, Haber R, Del Toro R, Hernandez V (2013) Self-adaptive systems: a survey of current approaches, research challenges and applications. Expert Syst Appl 40(18):7267–7279
Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518:529–533. https://doi.org/10.1038/nature14236
Moh M, Raju R (2018) Machine learning techniques for security of Internet of Things (IoT) and fog computing systems. In 2018 International Conference on High Performance Computing and Simulation (HPCS) pp 709–715.
Nguyen A (2016) A plan to prevent cyber criminals from sucessfully attacking the internet of things from the supply chain (Doctoral dissertation, Utica College).
Su J, Vasconcellos V, Prasad S, Daniele S, Feng Y, Sakurai K (2018) Lightweight classification of IoT malware based on image recognition, pp 664–669. https://doi.org/10.1109/COMPSAC.2018.10315
Vinod P, Zemmari A, Conti M (2019) A machine learning based approach to detect malicious android apps using discriminant system calls. Future Gener Comput Syst 94:333–350
Wei D, Qiu X (2018) Status-based detection of malicious code in internet of things (IoT) devices, pp 1–7. https://doi.org/10.1109/CNS.2018.8433183
Yang C, Xu Z, Gu G, Yegneswaran V, Porras P, Droidminer A (2014) Automated mining and characterization of fine-grained malicious behaviors in android applications, In European Symposium on Research in Computer Security pp 163–182.
Zolotukhin M, Hamalainen T (2018) On artificial intelligent malware tolerant networking for IoT, pp 1–6. https://doi.org/10.1109/NFV-SDN.2018.8725767
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Arul, E. Deep nonlinear regression least squares polynomial fit to detect malicious attack on IoT devices. J Ambient Intell Human Comput 12, 769–779 (2021). https://doi.org/10.1007/s12652-020-02075-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02075-y