超级会员免费看
本文提出了一种利用PE文件路径作为辅助输入的多视图神经网络模型，以提高静态恶意软件检测的准确性和检测率。通过对商业规模数据集的分析，表明模型能学习到文件路径中有价值的上下文信息，减少了假阴性率。同时，通过LIME可解释性分析验证了模型的合理性。
文章目录
Learning from Context: Exploiting and Interpreting File Path Information for Better Malware Detection
Sophos 一家基于算法的安全公司
abstract
老规矩，抄一遍摘要，理解句子结构
Machine learning classifiers used for static portable executable malware detection typically employ single numerical feature vector representations of each file as input with one or more target labels per file during training.
However, there is much orthogonal information that can be gleaned from the context in which the file was seen.
In this paper, we propose utilizing a static source of contextual information - n
订阅专栏 解锁全文
扫一扫
3963
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
