A review of advancements and applications of pre-trained language models in cybersecurity

Z Liu - 2024 12th International Symposium on Digital …, 2024 - ieeexplore.ieee.org
In this paper, we delve into the transformative role of pre-trained language models (PLMs) in
cybersecurity, offering a comprehensive examination of their deployment across a wide …

Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling

S Wu, F Lu, E Raff, J Holt - arxiv preprint arxiv:2410.23601, 2024 - arxiv.org
Online learning methods, like the seminal Passive-Aggressive (PA) classifier, are still highly
effective for high-dimensional streaming data, out-of-core processing, and other throughput …

Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation

S Mohseni, S Mohammadi, D Tilwani, Y Saxena… - arxiv preprint arxiv …, 2024 - arxiv.org
Malware authors often employ code obfuscations to make their malware harder to detect.
Existing tools for generating obfuscated code often require access to the original source …

ClarAVy: A Tool for Scalable and Accurate Malware Family Labeling

RJ Joyce, D Everett, M Fuchs, E Raff, J Holt - arxiv preprint arxiv …, 2025 - arxiv.org
Determining the family to which a malicious file belongs is an essential component of
cyberattack investigation, attribution, and remediation. Performing this task manually is time …