SOREL-20M: A large scale benchmark dataset for malicious PE detection

R Harang, EM Rudd - arxiv preprint arxiv:2012.07634, 2020 - arxiv.org
In this paper we describe the SOREL-20M (Sophos/ReversingLabs-20 Million) dataset: a
large-scale dataset consisting of nearly 20 million files with pre-extracted features and …

Automated machine learning for deep learning based malware detection

A Brown, M Gupta, M Abdelsalam - Computers & Security, 2024 - Elsevier
Deep learning (DL) has proven to be effective in detecting sophisticated malware that is
constantly evolving. Even though deep learning has alleviated the feature engineering …

Malware detection by control-flow graph level representation learning with graph isomorphism network

Y Gao, H Hasegawa, Y Yamaguchi, H Shimada - IEEE Access, 2022 - ieeexplore.ieee.org
With society's increasing reliance on computer systems and network technology, the threat
of malicious software grows more and more serious. In the field of information security …

[HTML][HTML] A study of the relationship of malware detection mechanisms using Artificial Intelligence

J Song, S Choi, J Kim, K Park, C Park, J Kim, I Kim - ICT Express, 2024 - Elsevier
Implementation of malware detection using Artificial Intelligence (AI) has emerged as a
significant research theme to combat evolving various types of malwares. Researchers …

Quo Vadis: hybrid machine learning meta-model based on contextual and behavioral malware representations

D Trizna - Proceedings of the 15th ACM Workshop on Artificial …, 2022 - dl.acm.org
We propose a hybrid machine learning architecture that simultaneously employs multiple
deep learning models analyzing contextual and behavioral characteristics of Windows …

{URET}: Universal Robustness Evaluation Toolkit (for Evasion)

K Eykholt, T Lee, D Schales, J Jang… - 32nd USENIX Security …, 2023 - usenix.org
Machine learning models are known to be vulnerable to adversarial evasion attacks as
illustrated by image classification models. Thoroughly understanding such attacks is critical …

Malware detection using LightGBM with a custom logistic loss function

Y Gao, H Hasegawa, Y Yamaguchi, H Shimada - IEEE Access, 2022 - ieeexplore.ieee.org
The increased spread of malicious software (malware) through the internet remains a
serious threat. Malware authors use obfuscation and deformation techniques to generate …

Stealing and evading malware classifiers and antivirus at low false positive conditions

M Rigaki, S Garcia - Computers & Security, 2023 - Elsevier
Abstract Model stealing attacks have been successfully used in many machine learning
domains, but there is little understanding of how these attacks work against models that …

Malware detection using attributed CFG generated by pre-trained language model with graph isomorphism network

Y Gao, H Hasegawa, Y Yamaguchi… - 2022 IEEE 46th …, 2022 - ieeexplore.ieee.org
Traditional malware detection methods cannot keep up with the massive amount of newly
created malware quickly and effectively. Machine learning is a promising method for the …

TCG-IDS: Robust Network Intrusion Detection via Temporal Contrastive Graph Learning

C Wu, J Sun, J Chen, M Alazab, Y Liu… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
In the era of zero trust security models and next-generation networks (NGN), the primary
challenge is that network nodes may be untrusted, even if they have been verified …