公开(公告)号：US20220272120A1

公开(公告)日：2022-08-25

申请号：US17183195

申请日：2021-02-23

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： YUANJIE LI ,  KYU-HAN KIM ,  QIANRU LI

IPC: H04L29/06

Abstract: Systems and methods for mitigating cyberattacks are described herein. A computing system can detect illegitimate network traffic associated with a cyberattack in network traffic. The computing system can determine an amplification factor of the cyberattack based in part on a probability distribution of the illegitimate network traffic. The computing system can determine a filter to demotivate a generation of the illegitimate network traffic. The determined filter can reduce the amplification factor of the cyberattack. The computing system can implement the determined filter to block the illegitimate network traffic.

公开(公告)号：US20210287066A1

公开(公告)日：2021-09-16

申请号：US16817251

申请日：2020-03-12

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： XIUFENG XIE ,  KYU-HAN KIM

IPC: G06N3/04 ,  G06N20/20 ,  G06N5/04

Abstract: Systems and methods are provided for an improved machine learning (ML) model system. The improved ML system can be configured to (1) initially classify the types of images and videos received by the various devices and provide the classified input to different ML models based on the classification (e.g., of the distortion level, etc.), and/or (2) reuse portions (referred to as base components) of each ML model where parameters of the base components are unchanged across the various ML models, while replacing other portions (referred to as adapted components) of the ML model where the parameters of the adapted components may change greatly.