IOT SECURITY MONITORING BASED ON

FUZZY OPTIMUM-PATH FOREST

CLASSIER

Presented by
Pradnya Patil

Guided by
Prof. Kamini Patil
Departmrnt of Computer Engineering
LGNSCOE, Nashik

Seminar Name LGNSCOE, Nashik 1

 OUTLINE…

• Introduction

• Literature Survey

• Problem Definition

• System Architecture

• Algorithm

• Advantages and Application

• Conclusion

• References.

Seminar Name LGNSCOE, Nashik 2

 INTRODUCTION

The Internet or the global Internet is the internationally connected

network of computer networks with addresses that are
administrated by IANA (Internet address and Naming Authority).
There are many aspects to security and many applications, ranging
from secure commerce and payments to private communications
and protecting passwords. One essential aspect for secure
communications is that of cryptography.
 PROBLEM DEFINITION

 At present, the Elgamal encryption algorithm works by sending

data to the receiver who has just one private key to decrypt the
data
 So In this project we are modifying the existing Elgamal
encryption algorithm by dividing the private key and assigning
them to 2n+1 authorized receivers individually. The persons
will be able to decrypt the message received from the sender
only if they are together, separately this operation being
impossible for them.

Seminar Name LGNSCOE, Nashik 4

 LITERATURE SURVEY

Serial Researcher ’s Year Future scope and Details

No. Name

1 J. Callas 15-22, 2007 "The Future of

Cryptography," Information
Systems Security,

2
J. L. Massey 3-25, 1986 "Cryptography—A selective
survey," Digital
Communications,

Seminar Name LGNSCOE, Nashik 5

3
K. Chachapara and 2013 "Secure sharing with
S. Bhadlawala cryptography in cloud,"
in 2013 Nirma
University International
Conference on
Engineering

4
S. B. Sadkhan Damascus, 2004 "Cryptography : current
status and future trends,"
in International
Conference on
Information and
Communication
Technologies: From
Theory to Applications,

5
N. Jirwan, A. Singh 1-6, 2013 "Review and Analysis of
and S. Vijay Cryptography
Techniques," International
Journal of Scientific &
Engineering Research,
vol. 3
 SUMMERY LITERATURE SURVEY

• Susan et al. [4] pointed out that network and computer security is a new and
fast-moving technology within the computer science field, with computer
security teaching to be a target that never stops moving. Algorithmic and
mathematic aspects, such as hashing techniques and encryption, are the
main focus of security courses. As crackers find ways to hack network
systems, new courses are created that cover the latest type of attacks, but
each of these attacks become outdated daily due to the responses from new
security software. With the continuous maturity of security terminology,
security techniques and skills continue to emerge in the practice of business,
network optimization, security architecture, and legal foundation.

Seminar Name LGNSCOE, Nashik 7

• Nitin Jirwan et al. [6] referred to data communication as depending
mainly on digital data communication, in which data security has the
highest priority when using encryption algorithms in order for data to
reach the intended users safely without being compromised. They
also demonstrated the various cryptographic techniques that are used
in the process of data communication, such as symmetric and
asymmetric methods. .

• Anjula Gupta et al. [8] showcased the origins and meaning of

cryptography as well as how information security has become a
challenging issue in the fields of computers and communications. In
addition to demonstrating cryptography as a way to ensure
identification, availability, integrity, authentication, and
confidentiality of users and their data by providing security and
privacy, this paper also provides various asymmetric algorithms that
have given us the ability to protect and secure data.
 SYSTEM ARCHITECTURE
Architecture of cryptography

Seminar Name LGNSCOE, Nashik 9

 ALGORITHM

Input :- G,T, λ , σ.
Output:- O,P,C
Auxiliary :- L, cst,p,Pmin,Pmax
1)

2)

For q in N do
density  p(q) using Equation 1;
o(q)  nil,p(q)  + ∞
membership  Fθ(q) using Equation 2;
 For q in T do
p(q)  O,C(q) = λ(q),L  q
While L ≠ Ø do
Remove from L a sample q such
that p(q) is minimum;
for u in N do
if q ≠ u and p(u)>p(q) then
cst  F θ(u)*max{p(q),d(q,u)};
if cst < p(u) and p(u) ≠ +∞ then
Remove u form L
C(u)  C(q) ,O(u) q,P(u) cst;
Lu;
Return[O,P,C]
 • Fuzzy OPF hyperparameter optimization considering Austin exas-
Scenario1 images over
• Find better alternatives for scenarios that have a greater degree of
complexity.
• To propose a supervised model to classify IoT network traffic into
intrusion and no intrusion packets.
• Improve sample selection and classifier output performance, also
contributing to alleviate some problems, such as: noise, unbalanced
classes and outliers.

12

Seminar Name LGNSCOE, Nashik 12

 13

Seminar Name LGNSCOE, Nashik 13

 CONCLUSION

• This approach is evaluated on two datasets based on real data from

intrusions in IOT networks, and performance compared with different
ML algorithms: SVM, KNN, LDA, Bayes, and OPF.
• The proposed model based on Fuzzy OPF reached 99.24% of true
positive cases. Therefore, we conclude that Fuzzy OPF isa relevant
classifier to generalize patterns of any threat that escapes the
abnormality of traffic in an IoT network.

15

Seminar Name LGNSCOE, Nashik 15

 REFERENCES

•H. M. Almohri, L. T. Watson, and D. Evans, “An attack resilient architecture

for the internet of things,” 15, pp. 3940–3954, 2020.
•Yongzhao Xu, Renato W. R. de Souza “Intelligent IoT Security Monitoring
based on Fuzzy Optimum-Path Forest Classifier”,2022.
• Z. Lv, L. Qiao, J. Li, and H. Song, “Deep learning enabled security issues in
the internet of things,” IEEE Internet of Things Journal, 2020.
•Butun, P. O¨ and H. Song, “Security of the internet of things: Vulnerabilities,
attacks, and counter measures,”,pp. 616–644, 2019.
•S. Sarkar, S. Chatterjee, and S. Misra, “Assessment of the suitability of fog
computing in the context of IOT,” ,pp. 46–59, 2015.

16

Seminar Name LGNSCOE, Nashik 16

 17

Seminar Name LGNSCOE, Nashik 17