AI Chat AI Image Generator AI Video Text to Speech

Defensive Distillation is Not Robust to Adversarial Examples

07/14/2016

∙

by Nicholas Carlini, et al.

∙

∙

We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks.

Nicholas Carlini
63 publications
David Wagner
24 publications

page 1

page 2

page 3

research

∙ 08/21/2019

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

Adversarial examples are artificially modified input samples which lead ...

1 Marcus Soll, et al. ∙

research

∙ 08/16/2016

Towards Evaluating the Robustness of Neural Networks

Neural networks provide state-of-the-art results for most machine learni...

0 Nicholas Carlini, et al. ∙

research

∙ 05/15/2017

Extending Defensive Distillation

Machine learning is vulnerable to adversarial examples: inputs carefully...

0 Nicolas Papernot, et al. ∙

research

∙ 05/25/2019

Adversarial Distillation for Ordered Top-k Attacks

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, espec...

1 Zekun Zhang, et al. ∙

research

∙ 03/14/2018

Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples

Deep Neural Networks (DNNs) have achieved remarkable performance in a my...

0 Zihao Liu, et al. ∙

research

∙ 06/14/2019

Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking

The rise of machine learning as a service and model sharing platforms ha...

0 Ziqi Yang, et al. ∙

research

∙ 02/02/2023

Dataset Distillation Fixes Dataset Reconstruction Attacks

Modern deep learning requires large volumes of data, which could contain...

0 Noel Loo, et al. ∙