GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
Well explain how the alerts that a typical security operations center receives are heterogeneous in severity, applicability, and origin. Centers are often overwhelmed and unable to investigate every alert, resulting in missed malicious activity. By leveraging RAPIDS data processing and analytic capabilities, we give analysts insights into these alerts. We also provide high-dimensional co-occurrence, trend identification, and rare event flagging. By reducing the noise floor and extracting additional signals and context from existing alerts, we decrease the time it takes for analysts to triage and investigate alerts. Well share what technologies and pipelines to use and how to integrate them into existing security environments.
Well explain how the alerts that a typical security operations center receives are heterogeneous in severity, applicability, and origin. Centers are often overwhelmed and unable to investigate every alert, resulting in missed malicious activity. By leveraging RAPIDS data processing and analytic capabilities, we give analysts insights into these alerts. We also provide high-dimensional co-occurrence, trend identification, and rare event flagging. By reducing the noise floor and extracting additional signals and context from existing alerts, we decrease the time it takes for analysts to triage and investigate alerts. Well share what technologies and pipelines to use and how to integrate them into existing security environments.  Back
 
Topics:
Cyber Security
Type:
Talk
Event:
GTC Washington D.C.
Year:
2019
Session ID:
DC91356
Download:
Share:
 
Abstract:

Rules-based approaches to cyber security detection do not scale and are burdened by a reliance on human engineering. In this session, we explore machine learning approaches to cyber security threats, specifically those related to failed login attempts (often a left-of-compromise indicator of an attack) and credential misuse (abnormal behavior). Rather than apply rules, we use the data processing and analytic capabilities of the GPU Open Analytics Initiative (GOAI) to accelerate model training, inference, and other steps necessary to provide actionable alerts to an analyst in near real-time.

Rules-based approaches to cyber security detection do not scale and are burdened by a reliance on human engineering. In this session, we explore machine learning approaches to cyber security threats, specifically those related to failed login attempts (often a left-of-compromise indicator of an attack) and credential misuse (abnormal behavior). Rather than apply rules, we use the data processing and analytic capabilities of the GPU Open Analytics Initiative (GOAI) to accelerate model training, inference, and other steps necessary to provide actionable alerts to an analyst in near real-time.

  Back
 
Topics:
Cyber Security, Artificial Intelligence and Deep Learning
Type:
Talk
Event:
GTC Washington D.C.
Year:
2018
Session ID:
DC8190
Streaming:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next