Certified AI Cyber Security Specialist Training

Cyber Security (AI) Specialist Course

Certified AI Cyber Security Specialist

Delivered by Industry Experts in AI and Cyber Security

Tools/Software used:
Python, Jupyter Notebook, Scikit-Learn, Keras, TensorFlow

Date: 4, 11, 18 & 25 Jul (Sat) 2020

1st in the Region

Register NowMore Info
Deep learning course

1st in the Region

Certified AI Cyber Security Specialist

Delivered by Industry Experts in AI and Cyber Security

Tools/Software used:
Python, Jupyter Notebook, Scikit-Learn, Keras, TensorFlow

Date: 4, 11, 18 & 25 Jul (Sat) 2020

Register NowMore InfoCyber Security Course

Objective of the AI Cyber Security Specialist Training

The Certified AI Cyber Security Specialist training aims to address how AI can transform Cyber-Security for Good and Bad, Applications of AI uses in Security (Engineering facilities) and Applications of AI misuses in Security.

AI Cyber Security course
  • Acquire knowledge as to how cyber criminals deploy machine learning and/or artificial intelligence tools to jeopardize cyber security in the forms of interference attacks, intrusions, poisoning of datasets and manipulating or corrupting secured models
  • Acquire quantitative and qualitative knowledge with respect to the deployment of machine learning and/or artificial intelligence tools to enhance cyber security in the detections of frauds, malwares and intrusions.
  • Acquire knowledge with respect to the deployment of machine learning and/or artificial intelligence tools to detect and mitigate cyber security threats in real-world applications in the areas of Autonomous vehicles, Water treatment plants and financial industry

Completion of the AI Python Training

The training will include several hands-on session to develop deep neural network algorithms to shadow, pre-detect and mitigate cyber-attacks

Course Outline
  • Unit 1: How is AI transforming cyber-security for good?
  • Unit 2: Deployment of ML/AI to detect specific cyber-security problems
  • Unit 3: How is AI transforming cyber-security for bad?
  • Unit 4: Deployment of engineered attacks on machine learning models
  • Unit 5: Cyber-attacks on water treatment facilities
  • Unit 6: Engineered attacks on water distribution systems
  • Unit 7: Engineered attacks on image recognition capability of autonomous vehicles
  • Unit 8: Engineered attacks on driving operational parameters (via manipulation of datasets)

Tools/Software used: Python, Jupyter Notebook, Scikit-Learn, Keras, TensorFlow

Duration
  • 32 hours (4 Days)
Course Outcome

Session 1

Fundamental quantitative and qualitative details to the deployment of machine learning and/or artificial intelligence tools to enhance cyber security in the detections of frauds, malwares and intrusions.

At the end of this session, participants will be able to:

  • Explain the causes and emergence of the different types of cyber-attacks and possible approaches to mitigate them
  • Explain the causes and emergence of frauds and quantitatively build suitable deep neural network model to mitigate fraud occurrences
  • Explain the causes and emergence of malwares and quantitatively build suitable deep neural network model to mitigate malwares occurrences
  • Explain the causes and emergence of intrusions and quantitatively build suitable deep neural network model to mitigate intrusions occurrences

Session 2

Fundamental quantitative and qualitative details to the deployment of machine learning and/or artificial intelligence tools to jeopardize cyber security in the forms of interference attacks, poisoning of datasets and manipulating or corrupting secured models.

At the end of this session, participants will be able to:

  • Explain the causes and emergence of the different types of attacks on machine learning and possible techniques to perform those attacks
  • Explain the usage of interference attacks and quantitatively build suitable deep neural network models to perform interference attacks
  • Explain the usage of data poisoning and quantitatively build suitable deep neural network models to perform data poisoning acts
  • Explain the usage of generative adversarial networks (GANs) and quantitatively build them to perform corrupt or manipulate secured models

Session 3

Fundamental quantitative and qualitative details to the deployment of machine learning and/or artificial intelligence tools to benefit cyber security in real-world applications.

At the end of this session, participants will be able to:

  • Explain the causes of cyber-attacks on water treatment facilities and quantitatively build suitable machine learning and/or artificial intelligence model to detect and/or mitigate those attacks
  • Explain the causes of engineered attacks, via cyber means, on water distribution pipes and quantitatively build suitable machine learning and/or artificial intelligence model to detect and/or mitigate those attacks

Session 4

Fundamental quantitative and qualitative details to the deployment of machine learning and/or artificial intelligence tools to jeopardize cyber security in real-world applications.

At the end of this session, participants will be able to:

  • Explain the causes of engineered attacks, via cyber means, on image recognition capabilities of autonomous vehicles and quantitatively build suitable machine learning and/or artificial intelligence model to perform those attacks
  • Explain the causes of engineered attacks, via cyber means, on driving operational parameters of vehicles and quantitatively build suitable machine learning and/or artificial intelligence model to perform those attacks

COPYRIGHT © 2019 GLOBAL ICT TRAINING & CERTIFICATION (GICT). ALL RIGHTS RESERVED.

Find out more

Visit our GICT course schedule to check our class availability.

What our participants say...

GICT Authorized Training Partners:

Philippines
Info-Alchemy | Global ICT Training | GICT Training Partners
India
HCL | Global ICT Training | GICT Training Partners

HCL Infosystems www.hclinfosystems.in

Find more GICT Training Partners here.

 

© Global ICT Training & Certification Pte Ltd. All rights reserved.