Multi-Level Generative Pretrained Transformer for Improving Malware Detection Performance

Generating diverse and realistic malware variants is critical to improve the performance of deep learning-based Malware Detection Systems (MDSs) and fight against an increasing number of complex malware attacks. Traditionally, researchers construct the single generative model based on the whole dataset, which may suffer from mode collapse and scalability problem. In order to overcome these problems, we propose Multi-level Generative Pretrained Transformer (MLGPT) which organizes multiple GPTs in the tree. Each GPT in the tree can learn the unique pattern of malware language for one malware subfamily. Consequently, MLGPT has great potentials to produce more diverse and realistic malware variants than the single generative model. Experimental results show that performance improvement of MLGPT is statistically significant as compared to the single generative model while the construction time of MLGPT is comparable to the single generative model due to the parallel strategy.

• Publication year

  2024

• Venue

  2024 7th International Conference on Artificial Intelligence and Big Data (ICAIBD)

• Publication date

  2024-05-24

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICAIBD62003.2024.10604442
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Mathematical Interpretation of Autoregressive Generative Pre-Trained Transformer and Self-Supervised Learning

  2023cited by this paper
• Malware Detection Issues, Challenges, and Future Directions: A Survey

  2022influential reference
• A novel method for improving the robustness of deep learning-based malware detectors against adversarial attacks

  2022cited by this paper
• Deep learning based cross architecture internet of things malware detection and classification

  2022cited by this paper
• Adversarial malware sample generation method based on the prototype of deep learning detector

  2022cited by this paper
• Generating Fake Cyber Threat Intelligence Using Transformer-Based Models

  2021cited by this paper
• Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

  2021cited by this paper
• Generative adversarial network to detect unseen Internet of Things malware

  2021cited by this paper
• Language Models are Few-Shot Learners

  2020influential reference
• MALGRA: Machine Learning and N-Gram Malware Feature Extraction and Detection System

  2020cited by this paper
• Generative Adversarial Network for Improving Deep Learning Based Malware Classification

  2019cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019influential reference
• Discovering Future Malware Variants By Generating New Malware Samples Using Generative Adversarial Network

  2019cited by this paper
• Data Augmentation with Generative Models for Improved Malware Detection: A Comparative Study*

  2019cited by this paper
• Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables

  2018cited by this paper
• SHARE

  2018cited by this paper
• Attention is All you Need

  2017cited by this paper
• A Survey on Malware Detection Using Data Mining Techniques

  2017influential reference
• Adversary Resistant Deep Neural Networks with an Application to Malware Detection

  2016cited by this paper
• Convolutional neural networks for malware classification

  2016cited by this paper
• Assessing the accuracy of prediction algorithms for classification: an overview

  2000cited by this paper
• Combined 5 x 2 cv F Test for Comparing Supervised Classification Learning Algorithms

  1999cited by this paper
• Combined 5 2 cv F Test for Comparing Supervised Classification Learning Algorithms

  1999cited by this paper
• K-means Clustering Algorithm for Categorical Attributes

  1999cited by this paper

• No citing papers are available for this paper.