文章摘要
李怡,李进.基于Ghost DenseNet SE的恶意代码检测方法[J].空军工程大学学报:自然科学版,2021,22(5):49-55
基于Ghost DenseNet SE的恶意代码检测方法
A Malicious Code Detection Method Based on Ghost DenseNet SE
  
DOI:
中文关键词: 恶意代码  轻量化卷积  密集连接网络  通道域注意力机制
英文关键词: malicious code  lightweight convolutional  densely connected network  channel domain attention mechanism
基金项目:malicious code; lightweight convolutional; densely connected network; channel domain attention mechanism
作者单位
李怡,李进 空军工程大学防空反导学院西安710051 
摘要点击次数: 77
全文下载次数: 64
中文摘要:
      针对现有恶意代码检测模型对恶意代码及其变种识别率不高,且参数量过大这一问题,将轻量化卷积Ghost、密集连接网络DenseNet与通道域注意力机制SE相结合,提出一种基于Ghost DenseNet SE的恶意代码家族检测模型。该模型为压缩模型体积、提升识别速率,将DenseNet中的标准卷积层替换为轻量化Ghost模块;并引入通道域注意力机制,赋予特征通道不同权重,用以提取恶意代码的关键特征,提高模型检测精度。在Malimg数据集上的实验结果表明,该模型对恶意代码家族的识别准确率可以达到99.14%,与AlexNet、VGGNet等模型相比分别提高了1.34%和2.98%,且模型参数量更低。该算法在提升分类准确率的同时,降低了模型复杂度,在恶意代码检测中具有重要的工程价值和实践意义。
英文摘要:
      Aimed at the problems that the existing malicious code detection model is iow in recognition rate of malicious code and its variants, and the amount of parameters is too large, a method of Malicious code family detection model is proposed based on Ghost DenseNet SE is proposed in combination with the lightweight convolutied Ghost, densely connected network DenseNet and the channel domain attention mechanism SE. This model serves as a type of compressing the model volume and improving the recognition rate. the standard convolutional layer in DenseNet is replaced with a lightweight Ghost module, and the channel domain attention mechanism is introduced to assign different weights to the feature channels to extract the key features of malicious code and improve model checking accuracy. The experimental results on the Malimg data set show that the models recognition accuracy of malicious code families can reach 9914%, Compared with AlexNet and VGGNet, the recognition accuracy increases by 1.34% and 2.98% respectively, and the amount of model parameters is lower. This algorithm not only improves the classification accuracy, but also reduces the complexity of the model. The algorithm has important engineering value and practical significance in malicious code detection.
查看全文   查看/发表评论  下载PDF阅读器
关闭