Malware Detection Using Transformers-based Model GPT-2

Şahin, Nazenin
The variety of malicious content, besides its complexity, has significantly impacted end-users of the Information and Communication Technologies (ICT). To mitigate the effect of malicious content, automated machine learning techniques have been developed to proactively defend the user systems against malware. Transformers, a category of attention-based deep learning techniques, have recently been shown to be effective in solving various malware problems by mainly employing Natural Language Processing (NLP) methods. In the present study, we propose a Transformers architecture to detect malicious software automatically. We present models based on GPT-2 (Generative Pre-trained Transformer 2), which performs assembly code obtained from a static analysis on PE (Portable Executable) files. We generated a pre-trained model to capture various characteristics of both malicious and benign assembly codes. That improves the model’s detection performance. Moreover, we created a binary classification model that used preprocessed features to characterize existing malicious and benign code pieces. The resulting binary classification model distinguishes between those code pieces by recognizing novel malware or benign assembly codes. Finally, we used GPT -2's pre-trained model to improve detection accuracy. The experiments showed that a fine-tuned pre-trained model and GPT-2's pre-trained model led to accuracy values up to 85.4\% and 78.3\%, respectively.


Static Malware Detection Using Stacked Bi-Directional LSTM
Demirci, Deniz; Acartürk, Cengiz; Department of Cybersecurity (2021-8-19)
The recent proliferation in the use of the Internet and personal computers has made it easier for cybercriminals to expose Internet users to widespread and damaging threats. In order protect the end users against such threats, a security system must be proactive. It needs to detect malicious files or executables before reaching the end-user. To create an efficient and low-cost malware detection mechanism, in the present study, we propose stacked bidirectional long short-term memory (Stacked BiLSTM) based de...
Empirical investigation of Internet banking usage in Turkey
Daneshgadeh, Salva; Özkan Yıldırım, Sevgi; Department of Information Systems (2013)
With the fast development of Information and Communication Technologies (ICT), internet banking has become more popular worldwide. This study empirically investigates the factors impact internet banking usage by Turkish bank customers. A unique Internet Banking Usage Model (IBUM) was developed in this study. The proposed model incorporated 10 factors named usefulness, ease of use, compatibility, control, social influence, risk, website features, alliance service, awareness of service and customization/perso...
Malicious code detection: run trace analysis by LSTM
Şırlancı, Melih; Acartürk, Cengiz; Gürkan Balıkçıoğlu, Pınar; Department of Cybersecurity (2021-6)
Malicious software threats and their detection have been gaining importance as a subdomain of information security due to the expansion of ICT applications in daily settings. A major challenge in designing and developing anti-malware systems is the coverage of the detection, particularly the development of dynamic analysis methods that can detect polymorphic and metamorphic malware efficiently. In the present study, we propose a methodological framework for detecting malicious code by analyzing run trace ou...
Investigation of Fatih Project within the scope of teachers school administrators and yegıtek adminisrators opinions A multiple case study
Gök, Ali; Yıldırım, Zahide (Mersin Üniversitesi, 2015-01-01)
Information and Communication Technologies (ICT) affected educational environments as well as other areas. Recently, in Turkey, the government has initiated a project, FATİH Project (Movement of Enhancing Opportunities and Improving Technology Project). In this project, some technologies have been installed in K-12 schools all over the country. For the success of the FATİH Projects, not only how teachers perceive those technologies, but also what the school administrators’ and project administrators’ opinio...
Using operational data for decision making a feasibility study in rail maintenance
Marsh, William; Nur, Khalid; Yet, Barbaros; Majumdar, Arnab (2016-05-01)
In many organisations, large databases are created as part of the business operation: the promise of ‘big data’ is to extract information from these databases to make smarter decisions. We explore the feasibility of this approach for better decision-making for maintenance, specifically for rail infrastructure. We argue that the data should be used within a Bayesian framework with the aim of inferring the underlying state of the system so we can predict future failures and improve decision-making. Within thi...
Citation Formats
N. Şahin, “Malware Detection Using Transformers-based Model GPT-2,” M.S. - Master of Science, Middle East Technical University, 2021.