Malware Detection
Malware detection research aims to develop robust and efficient methods for identifying malicious software, focusing on overcoming challenges like obfuscation and the emergence of novel attack techniques. Current efforts concentrate on leveraging deep learning architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and large language models (LLMs), often incorporating techniques like transfer learning, self-supervised learning, and few-shot learning to improve accuracy and generalization. These advancements are crucial for enhancing cybersecurity defenses across various platforms (Windows, Android, IoT) and mitigating the ever-evolving threat landscape, with a growing emphasis on explainable AI to increase transparency and trust in automated detection systems.
Papers
Transformers for End-to-End InfoSec Tasks: A Feasibility Study
Ethan M. Rudd, Mohammad Saidur Rahman, Philip Tully
Efficient Malware Analysis Using Metric Embeddings
Ethan M. Rudd, David Krisiloff, Scott Coull, Daniel Olszewski, Edward Raff, James Holt
From Malware Samples to Fractal Images: A New Paradigm for Classification. (Version 2.0, Previous version paper name: Have you ever seen malware?)
Ivan Zelinka, Miloslav Szczypka, Jan Plucar, Nikolay Kuznetsov