首页> 外国专利> SYSTEM FOR DETECTING TROJANS IN AN ARTIFICIAL NETWORK AND METHOD THEROF

SYSTEM FOR DETECTING TROJANS IN AN ARTIFICIAL NETWORK AND METHOD THEROF

机译:用于检测人工网络中的特洛伊木马的系统及其方法

摘要

A system and method is provided that tests and determines whether candidate artificial intelligence model contains a Trojan from when it was trained and using the outcome determination of the Trojan to determine whether the candidate artificial intelligence model should be deployed. The system utilizes a first artificial intelligence that operates as a data generator and a second artificial intelligence that operates as a discriminator to determine whether the candidate artificial intelligence contains a Trojan. The first artificial intelligence combines sets of data with random Trojan triggers and the second artificial intelligence discriminates output classifications from the candidate artificial intelligence model to determine whether the Trojan is present based on probability outputs.
机译:提供了一个系统和方法,即测试和确定候选人工智能模型是否包含从培训并使用木马的结果确定,以确定是否应该部署候选人工智能模式。 该系统利用作为数据发生器的第一人工智能,作为数据发生器,第二人工智能操作,作为鉴别器,以确定候选人工智能是否包含特洛伊木马。 第一人工智能将数据组合与随机的木马触发器,第二人工智能区分从候选人工智能模型的输出分类,以确定特洛伊木马是否存在基于概率输出。

著录项

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