DETEKSI SERANGAN DDOS PADA SISTEM SMARTHOME DENGAN METODE DEEP LEARNING

FATIH, ALDI HOIRUL and Stiawan, Deris and Afifah, Nurul (2025) DETEKSI SERANGAN DDOS PADA SISTEM SMARTHOME DENGAN METODE DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011282126069_cover.jpg] Image
RAMA_56201_09011282126069_cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (64kB)
[thumbnail of RAMA_56201_09011282126069.pdf] Text
RAMA_56201_09011282126069.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_TURNITIN.pdf] Text
RAMA_56201_09011282126069_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_01_front_ref.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (636kB)
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_02.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (638kB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_03.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_04.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_05.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (211kB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_06_ref.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (190kB) | Request a copy
[thumbnail of RAMA_56201_09011282126069_0003047905_8958340022_07_lamp.pdf] Text
RAMA_56201_09011282126069_0003047905_8958340022_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy

Abstract

The advancement of the Internet of Things (IoT) enables physical devices such as cameras, home doors, televisions, lights, and other household appliances to connect to the internet, forming an intelligent and convenient Smart Home system. However, the connectivity among these heterogeneous devices also increases vulnerability to cyberattacks, particularly Distributed Denial of Service (DDoS) attacks. In this study, Deep Learning methods, specifically Deep Neural Networks (DNN) and Autoencoders (AE), are employed to detect DDoS attacks within the dataset. Tools such as the Snort Intrusion Detection System (IDS) are utilized to identify DDoS attacks, while CICFlowMeter is used to extract data from pcap format into csv format. The results of this study demonstrate that the Autoencoder method effectively performs feature extraction and dimensionality reduction, achieving optimal performance using an 80% training and 20% testing split, with a training loss of 0.0052 and validation loss of 0.0054. The features are then classified using a Deep Neural Network with 250 epochs, yielding evaluation metrics of 99.53% accuracy, 99.53% precision, 99.53% recall, and 99.53% F1- score.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Internet of Things, Smart home, Distributed Denial of Service, Snort, CICFlowMeter, Deep Learning, Deep Neural Network, Autoencoder.
Subjects: T Technology > T Technology (General) > T57.6-57.97 Operations research. Systems analysis > T57.85 Network systems theory Including network analysis Cf. TS157.5+ Scheduling
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Aldi Hoirul Fatih
Date Deposited: 30 Jun 2025 02:03
Last Modified: 30 Jun 2025 02:03
URI: http://repository.unsri.ac.id/id/eprint/176055

Actions (login required)

View Item View Item