电子学报2025，Vol.53Issue(3)：849-863,15.DOI:10.12263/DZXB.20240746
基于多维度动态加权alpha图像融合与特征增强的恶意软件检测方法
Malware Detection Method Based on Multi-Dimensional Dynamic Weighted Alpha Image Fusion and Feature Enhancement
摘要
Abstract
Existing malware detection methods suffer from inadequate extraction of sample features,excessive reli-ance on domain expert knowledge,and operational behavior monitoring,significantly impacting detection and classification performance.To address these issues,we propose a malware detection method based on multidimensional dynamic weight-ed alpha image fusion and feature enhancement.Standardized sample sets are obtained through invalid sample cleaning and outlier processing.High-quality fused image samples are then generated using a three-channel image generation and multidi-mensional dynamic weighted alpha image fusion method.The puppet optimization algorithm is employed for data recon-struction to mitigate the impact of data class imbalance on detection results,and image enhancement is performed on the re-constructed data samples.A spatial attention enhancement network based on dual-branch feature extraction and fusion chan-nel information representation is used to extract and enhance image and text features,thereby improving feature representa-tion capabilities.The enhanced image and text features are fused using a weighted fusion method to achieve malware family detection and classification.Experimental results show that the proposed method achieves a malware detection classifica-tion accuracy of 99.72%on the BIG2015 dataset,representing an improvement of 0.22～2.50 percentage points over existing detection methods.关键词
恶意软件检测/图像融合/傀儡优化算法/双分支特征提取/数据重构/特征增强Key words
malware detection/image fusion/puppet optimization algorithm/dual-branch feature extraction/data re-construction/feature enhancement分类
计算机与自动化引用本文复制引用
谢丽霞,魏晨阳,杨宏宇,胡泽,成翔..基于多维度动态加权alpha图像融合与特征增强的恶意软件检测方法[J].电子学报,2025,53(3):849-863,15.基金项目
国家自然科学基金(No.62201576,No.U1833107) （No.62201576,No.U1833107）
江苏省基础研究计划自然科学基金(No.BK20230558) National Natural Science Foundation of China(No.62201576,No.U1833107) （No.BK20230558）
Basic Research Program Natural Science Foundation of Jiangsu Province(No.BK20230558) （No.BK20230558）
