Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Alam, Mohammad Mahmudul, Raff, Edward, Biderman, Stella, Oates, Tim, Holt, James
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909152095240192
author Alam, Mohammad Mahmudul
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
author_facet Alam, Mohammad Mahmudul
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
contents Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long-range techniques and benchmarks and find that they're not very suitable in this problem area. In this paper, we introduce Holographic Global Convolutional Networks (HGConv) that utilize the properties of Holographic Reduced Representations (HRR) to encode and decode features from sequence elements. Unlike other global convolutional methods, our method does not require any intricate kernel computation or crafted kernel design. HGConv kernels are defined as simple parameters learned through backpropagation. The proposed method has achieved new SOTA results on Microsoft Malware Classification Challenge, Drebin, and EMBER malware benchmarks. With log-linear complexity in sequence length, the empirical results demonstrate substantially faster run-time by HGConv compared to other methods achieving far more efficient scaling even with sequence length $\geq 100,000$.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17978
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Alam, Mohammad Mahmudul
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
Cryptography and Security
Artificial Intelligence
Machine Learning
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long-range techniques and benchmarks and find that they're not very suitable in this problem area. In this paper, we introduce Holographic Global Convolutional Networks (HGConv) that utilize the properties of Holographic Reduced Representations (HRR) to encode and decode features from sequence elements. Unlike other global convolutional methods, our method does not require any intricate kernel computation or crafted kernel design. HGConv kernels are defined as simple parameters learned through backpropagation. The proposed method has achieved new SOTA results on Microsoft Malware Classification Challenge, Drebin, and EMBER malware benchmarks. With log-linear complexity in sequence length, the empirical results demonstrate substantially faster run-time by HGConv compared to other methods achieving far more efficient scaling even with sequence length $\geq 100,000$.
title Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2403.17978