Tensorflow, there is no spoon
summary
Covers adversarial examples for neural networks using TensorFlow: demonstrates how to generate adversarial images that fool models (e.g., classifiers used in self-driving cars, face recognition, security cameras) and presents defensive techniques to protect models from such attacks.
AI-written summary · about
chapters (15)
- 0:00Intro
- 0:25There is no spoon
- 1:31The Matrix
- 3:43Panda vs Gibbon
- 4:59Other examples
- 5:49Perturbation
- 9:32Turtles
- 11:58Layers
- 15:00Decision Boundary
- 18:23Making an image
- 19:34Inception V3
- 20:30Cat classification
- 25:17Results
- 28:06Gaen
- 31:57This person does not exist
related talks
43mTensorflow, there is no spoon
45mTensorflow, there is no spoon
31mNo Tensorflow, there is no spoon!
25mTricking Neural Networks : Explore Adversarial Attacks
36mAdversarial Attacks on Deep Learning
38mUsing adversarial samples to robustify your Neural Network Models
44mTensorflow, Tensorflow, What is it that you see?
21mTricking Neural Networks : Explore Adversarial Attacks