IEEE Consumer Electronics Magazine - January/February 2024 - 37

by utilizing open-source modules of ZEEK-IDS
(formerly BRO-IDS). In addition, Zeek14 (an
open-source software framework for analyzing
network traffic) generated logs (dns.log, conn.
log, http.log) are consolidated during the profile
generation phase to gain in-depth insight of
a specific IP's DNS sequences.
CONCLUSION
Accurate detection of cyber-attacks in modern-day
industrial control systems is undeniably
necessary to increase resilience and ensure
uninterrupted productivity with desired outcomes,
for which IDS had been considered a
promising second line of defense. Although the
shortcomings of conventional intrusion-detection
protocols have been addressed with
machine-learning models, runtime threat alarms
predominantly end up as -FP due to the voluminous
data of the industrial systems. To this end,
this article presents and discusses the integration
of a stacked neural network with an opensource
IDS for effective cyber-attack detection in
deployment-centric industrial systems that have
been an unexplored future work in state-of-theart
presented so far. Although the proposed IDS
portrays as a promising open-source consumer
technology that could be deployed alongside a
firewall, the trained weight matrix that the IDSclassifier
utilizes for discriminating the cyberincidents
could be meddled by the cyber-attackers.
Hence, matrix encryption or including an encoder
at the learning phase and a decoder at the classification
phase would be an obligatory future direction
of this research. In addition, most industrial traffic
is inherently multiresolution in nature, capturing
significant temporal noise that could aid the learning
model in gaining deeper insights into the CPS
behavior. Thus, in future, extending the modeled
neural-network stack with a wavelet-based activation
layer could improve incremental learning during
real-time threat analysis.
ACKNOWLEDGMENTS
The authors would like to thank SASTRA
Deemed University, Thanjavur, for providing the
infrastructure to carry out this research work.
This work was supported by The Ministry of
January/February 2024
Electronics and Information Technology (MeitY),
India, under Grant AAA-22/7/2018-CSRD-MeitY.
&REFERENCES
1. S. S. Jagtap, V. S. Shankar Sriram, and V.
Subramaniyaswamy, " A hypergraph based Kohonen
map for detecting intrusions over cyber-physical
systems traffic, " Future Gener. Comput. Syst., vol. 119,
pp. 84-109, 2021, doi: 10.1016/j.future.2021.02.001.
2. K. Stouffer, V. Pillitteri, S. Lightman, M. Abrams, and A.
Hahn, Guide to Industrial Control Systems (ICS)
Security. Gaithersburg, MD, USA: Nat. Inst. Standards
Technol., Jun. 2015, doi: 10.6028/NIST.SP.800-82r2.
3. T. Baker, M. Mackay, A. Shaheed, and B. Aldawsari,
" Security-oriented cloud platform for SOA-based
SCADA, " in Proc. 15th IEEE/ACM Int. Symp. Cluster,
Cloud Grid Comput., 2015, pp. 961-970, doi: 10.1109/
CCGrid.2015.37.
4. National Cybersecurity and Communications
Integration Center, " ICS-CERT annual assessment
report: Industrial control systems cyber emergency
response team - FY2016, " 2016. [Online]. Available:
https://us-cert.cisa.gov/ics
5. S. Priyanga, M. R. Gauthama Raman, S. S. Jagtap, N.
Aswin, K. Kirthivasan, and V. S. Shankar Sriram, " An
improved rough set theory based feature selection
approach for intrusion detection in SCADA systems, "
J. Intell. FuzzySyst., vol. 36, no. 5, pp. 3993-4003,
2019, doi: 10.3233/JIFS-169960.
6. S. S. Jagtap and V. S. Shankar Sriram, " Subtree
hypergraph-based attack detection model for
signature matching over SCADA HMI, " Commun.
Comput. Inf. Sci., vol. 1116, pp. 173-184, 2019,
doi: 10.1007/978-981-15-0871-4_13.
7. H. A. Glory, C. Vigneswaran, S. S. Jagtap, R. Shruthi, G.
Hariharan, andV. S. S. Sriram, " AHW-BGOA-DNN:A
novel deep learningmodel for epileptic seizure
detection, " NeuralComput. Appl., vol. 33, no. 11,
pp. 6065-6093, 2021, doi: 10.1007/s00521-020-05384-7.
8. D. Wolpert, " Stacked generalization (Stacking), "
Neural Netw., vol. 5, pp. 241-259, 1992, doi: 10.1016/
S0893-6080(05)80023-1.
9. K. He, X. Zhang, S. Ren, and J. Sun, " Deep residual
learning for image recognition, " in Proc. IEEEConf.
Comput. Vis. Pattern Recognit., 2016, pp. 770-778.
10. R. C. Borges Hink, J. M. Beaver, M. A. Buckner, T. Morris,
U. Adhikari, and S. Pan, " Machine learning for power
systemdisturbance and cyber-attack discrimination, " in
Proc. 7th Int. Symp.ResilientControlSyst., 2014, pp. 1-8,
doi: 10.1109/ISRCS.2014.6900095.
37

https://doi.org/10.1016/j.future.2021.02.001 https://doi.org/10.6028/NIST.SP.800-82r2 https://doi.org/10.1109/CCGrid.2015.37 https://doi.org/10.1109/CCGrid.2015.37 https://us-cert.cisa.gov/ics https://doi.org/10.3233/JIFS-169960 https://doi.org/10.1007/978-981-15-0871-4_13 https://doi.org/10.1007/s00521-020-05384-7 https://doi.org/10.1016/S0893-6080(05)80023-1 https://doi.org/10.1016/S0893-6080(05)80023-1 https://doi.org/10.1109/ISRCS.2014.6900095

IEEE Consumer Electronics Magazine - January/February 2024

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - January/February 2024