Visible to the public SSH and FTP brute-force Attacks Detection in Computer Networks: LSTM and Machine Learning Approaches

TitleSSH and FTP brute-force Attacks Detection in Computer Networks: LSTM and Machine Learning Approaches
Publication TypeConference Paper
Year of Publication2020
AuthorsHossain, M. D., Ochiai, H., Doudou, F., Kadobayashi, Y.
Conference Name2020 5th International Conference on Computer and Communication Systems (ICCCS)
Date PublishedMay 2020
ISBN Number978-1-7281-6136-5
Keywordsanomaly detection, brute force attacks, brute-force, Computer Network Attacks, computer network security, Deep Learning, deep learning., Dictionaries, dictionary-based brute-force attacks, FTP, high-level attacks, Human Behavior, human factors, Internet, Intrusion detection, learning (artificial intelligence), long short-term memory deep learning approach, LSTM, machine learning, machine learning algorithms, machine learning approaches, machine learning classifiers, MLP, Network security, network traffic anomaly detection, password, pattern classification, policy-based governance, pubcrawl, SSH, telecommunication traffic

Network traffic anomaly detection is of critical importance in cybersecurity due to the massive and rapid growth of sophisticated computer network attacks. Indeed, the more new Internet-related technologies are created, the more elaborate the attacks become. Among all the contemporary high-level attacks, dictionary-based brute-force attacks (BFA) present one of the most unsurmountable challenges. We need to develop effective methods to detect and mitigate such brute-force attacks in realtime. In this paper, we investigate SSH and FTP brute-force attack detection by using the Long Short-Term Memory (LSTM) deep learning approach. Additionally, we made use of machine learning (ML) classifiers: J48, naive Bayes (NB), decision table (DT), random forest (RF) and k-nearest-neighbor (k-NN), for additional detection purposes. We used the well-known labelled dataset CICIDS2017. We evaluated the effectiveness of the LSTM and ML algorithms, and compared their performance. Our results show that the LSTM model outperforms the ML algorithms, with an accuracy of 99.88%.

Citation Keyhossain_ssh_2020