AI & ML in Cyber Security - Why Algorithms Are Dangerous

AI & ML in Cyber Security - Why Algorithms Are Dangerous

Black Hat via YouTube Direct link

ND STEP - GROUP NODES

20 of 26

20 of 26

ND STEP - GROUP NODES

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

AI & ML in Cyber Security - Why Algorithms Are Dangerous

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 RAFFAEL MARTY
  3. 3 OUTLINE
  4. 4 ML AND AI - WHAT IS IT? MACHINE LEARNING Algorithmic ways to describe data Supervised
  5. 5 MACHINE LEARNING USES IN SECURITY
  6. 6 FAMOUS AI (ALGORITHM) FAILURES
  7. 7 WHAT MAKES ALGORITHMS DANGEROUS? ALGORITHMS MAKE ASSUMPTIONS ABOUT THE DATA
  8. 8 COGNITIVE BIASES
  9. 9 THE DANGERS WITH DEEP LEARNING - WHEN NOT TO USE IT
  10. 10 ADVERSARIAL MACHINE LEARNING
  11. 11 DEEP LEARNING - THE SOLUTION TO EVERYTHING
  12. 12 UNSUPERVISED TO THE RESCUE?
  13. 13 UNDERSTAND AND CLEAN THE DATA
  14. 14 ENGINEERING DISTANCE FUNCTIONS
  15. 15 CHOOSING THE RIGHT UNSUPERVISED ALGORITHM
  16. 16 CHOOSING THE CORRECT ALGORITHM PARAMETERS
  17. 17 INTERPRETING THE DATA
  18. 18 A DIFFERENT APPROACH - PROBABILISTIC INFERENCE Rather than running algorithms the model the shape of data, we need to take expert knowledge/ domain expertise into account
  19. 19 ST STEP-BUILD THE GRAPH
  20. 20 ND STEP - GROUP NODES
  21. 21 RD STEP - INTRODUCE DEPENDENCIES
  22. 22 TH STEP - ESTIMATE PROBABILITIES
  23. 23 TH STEP-GOAL COMPUTATION
  24. 24 TH STEP-OBSERVE ACTIVITIES
  25. 25 TH STEP-EXPERT INPUT Strengthen the network by introducing expert knowledge
  26. 26 BELIEF NETWORKS - SOME OBSERVATIONS

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.