Aplikace umělých neuronových sítí pro detekci malware v HTTPS komunikaci
Thesis title in Czech: | Aplikace umělých neuronových sítí pro detekci malware v HTTPS komunikaci |
---|---|
Thesis title in English: | Application of artificial neural networks for malware detection in HTTPS traffic |
Key words: | Umělé neuronové sítě, detekce malware, HTTPS data, podobnostní hledání |
English key words: | Artificial neural networks, malware detection, HTTPS traffic, similarity search |
Academic year of topic announcement: | 2016/2017 |
Thesis type: | Bachelor's thesis |
Thesis language: | angličtina |
Department: | Department of Software Engineering (32-KSI) |
Supervisor: | doc. RNDr. Jakub Lokoč, Ph.D. |
Author: | hidden - assigned and confirmed by the Study Dept. |
Date of registration: | 09.05.2017 |
Date of assignment: | 10.05.2017 |
Confirmed by Study dept. on: | 06.06.2017 |
Date and time of defence: | 06.09.2017 00:00 |
Date of electronic submission: | 20.07.2017 |
Date of submission of printed version: | 21.07.2017 |
Date of proceeded defence: | 06.09.2017 |
Opponents: | RNDr. Mgr. Petr Somol, Ph.D. |
Guidelines |
Since a huge portion of malicious software communicates over the Internet, infected computers can be detected purely on the basis of their network activity. In order to avoid detection, malware designers have shifted to HTTPS protocol, thus limiting the amount of information to reveal the malware. In the thesis, the author will use neural networks to detect malicious communication on the basis of available HTTPS traffic metadata (number of bytes sent/received, time, etc.). The author will do a comparison of neural network architectures for classification and also explore methods for similarity search in HTTPS data. |
References |
Deep Learning. Ian J. Goodfellow, Yoshua Bengio, Aaron Courville. MIT Press 2016.
Maxout Networks. Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua Bengio. arXiv: 1302.4389. FaceNet: A Unified Embedding for Face Recognition and Clustering. Florian Schroff, Dmitry Kalenichenko, James Philbin. arXiv: 1503.03832. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdino. Journal of Machine Learning Research 15 (2014) 1929-1958. |