Evaluating Neural Network Robustness - Targeted Attacks and Defenses

Evaluating Neural Network Robustness - Targeted Attacks and Defenses

UCF CRCV via YouTube Direct link

Intro

1 of 13

1 of 13

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Evaluating Neural Network Robustness - Targeted Attacks and Defenses

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

  1. 1 Intro
  2. 2 Summary: Terminology (cont.) Targeted Attack Metrics
  3. 3 Existing Attacks
  4. 4 Fast Gradient Sign (FGS)
  5. 5 Jacobian-based Saliency Map Attack (SMA)
  6. 6 New approach
  7. 7 Objective Functions Explored
  8. 8 Dealing with Box Constraints: x+8 € [0, 1]
  9. 9 Finding Best Combination
  10. 10 Different Attacks (Cont.)
  11. 11 Attack Evaluation
  12. 12 Attacks on ImageNet
  13. 13 Defensive Distillation

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.