首页> 外国专利> SYSTEM AND METHOD OF IDENTIFYING MALICIOUS FILES USING LEARNING MODEL TRAINED ON MALICIOUS FILE

SYSTEM AND METHOD OF IDENTIFYING MALICIOUS FILES USING LEARNING MODEL TRAINED ON MALICIOUS FILE

机译:利用在恶意文件上训练的学习模型识别恶意文件的系统和方法

摘要

To provide a system and a method for identifying malicious files using a learning model trained on a malicious file.SOLUTION: A method includes the steps of: selecting a malicious file; selecting a plurality of safe files from a set of safe files that are known to be safe; generating, using a hardware processor, a learning model by training a neural network with the malicious file and the plurality of safe files; generating, using the hardware processor, rules for detection of malicious files from the learning model; determining, using the hardware processor, whether attributes of an unknown file fulfill the rules of detection of malicious files using the learning model; and identifying, using the hardware processor, the unknown file as malicious when determining the rules of detection are fulfilled.SELECTED DRAWING: Figure 3
机译:提供一种使用在恶意文件上训练的学习模型来识别恶意文件的系统和方法。解决方案:一种方法包括以下步骤:选择恶意文件;从一组已知安全的安全文件中选择多个安全文件;使用硬件处理器,通过用所述恶意文件和所述多个安全文件训练神经网络来生成学习模型;使用硬件处理器生成用于从学习模型检测恶意文件的规则;使用硬件处理器确定未知文件的属性是否满足使用学习模型检测恶意文件的规则;并在确定检测规则得到满足时使用硬件处理器将未知文件识别为恶意文件。图3

著录项

  • 公开/公告号JP2020009415A

    专利类型

  • 公开/公告日2020-01-16

    原文格式PDF

  • 申请/专利权人 AO KASPERSKY LAB;

    申请/专利号JP20190076577

  • 发明设计人 SERGEY V PROKUDIN;ALEXEY M ROMANENKO;

    申请日2019-04-12

  • 分类号G06F21/56;G06N3/08;

  • 国家 JP

  • 入库时间 2022-08-21 11:36:44

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号