عنوان

Intrusion Detection in IoT Systems Using Machine Learning Algorithms

Number

TLpq2423767658

.Language of Text, Soundtrack etc

انگلیسی

Title Proper

Intrusion Detection in IoT Systems Using Machine Learning Algorithms

General Material Designation

[Thesis]

First Statement of Responsibility

Basalan, Abdurrahman

Subsequent Statement of Responsibility

Salam, Mohammad Abdus

Name of Publisher, Distributor, etc.

Southern University and Agricultural and Mechanical College

Date of Publication, Distribution, etc.

2020

Specific Material Designation and Extent of Item

66

Dissertation or thesis details and type of degree

M.S.

Body granting the degree

Southern University and Agricultural and Mechanical College

Text preceding or following the note

2020

Text of Note

In recent years, Internet of Things (IoT) has grown up rapidly and tremendously. This growth has brought big and special problems. Two of the urgent topics of problems are security and privacy for IoT devices. Those devices are creating and gathering all data in their connections. For the security of IoT, detection of anomaly attacks is the first and crucial point for avoiding any interruption in the connection. Machine Learning algorithms have been rising and improving substantially year by year. Many classic tests can detect large amount of attacks in current time. However, those techniques are not enough for security since the types of attacks are changing and getting stronger frequently. In this study, we propose that how we can improve security level of IoT. Also, deep learning techniques, especially Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) have been applied in order to have better accuracy performance. Dataset is presumably one of the most important starting point for the use of those techniques. UNSW-NB15 dataset which is publicly available has been used for this study. Two different models are created in this study. One detects attack or no attack and another detects what type of attack or no attack. The combinations of LSTM and CNN algorithms have 98.2% accuracy which is best performance within the selected algorithms.

Artificial intelligence

Computer science

Basalan, Abdurrahman

Salam, Mohammad Abdus

Electronic name

p

[Thesis]

276903

a

Y