Logout succeed
Logout succeed. See you again!
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks .key PDF
39 Pages
2016
9.78 MB
EnglishPreview Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks .key
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, and Ananthram Swami May 24th, 2016 @ 37th IEEE Symposium on Security and Privacy @NicolasPapernot 1 M components N components p0=0.01 … p1=0.93 … … … “Type a quote here.” p8=0.02 { pN=0.01 –Johnny Appleseed Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron Weighted Link (weight is a parameter part of ✓ ) O 2 M components N components p0=0.01 … p1=0.02 … … … “Type a quote here.” p8=0.89 { pN=0.01 –Johnny Appleseed Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron Weighted Link (weight is a parameter part of ✓ ) O 3 4 Deep Learning for Classification 5 M components N components … … … { Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron ✓ Weighted Link (weight is a parameter part of ) O 6 M components N components … … … { Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron ✓ Weighted Link (weight is a parameter part of ) O 7 M components N components … … … { Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron ✓ Weighted Link (weight is a parameter part of ) O 8 M components N components … … … { Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron ✓ Weighted Link (weight is a parameter part of ) O 9 M components N components … … … { Input Layer Hidden Layers Output Layer (e.g., convolutional, rectified linear, …) Neuron ✓ Weighted Link (weight is a parameter part of ) O 10
