Fetching the paper…

Reading the bibliography…

2017

Training Ensembles to Detect Adversarial Examples

Bagnall, Alexander, Bunescu, Razvan, Stewart, Gordon

Original
PDF
Post on X

Understand

We propose a new ensemble method for detecting and classifying adversarial examples generated by state-of-the-art attacks, including DeepFool and C&W.

Our method works by training the members of an ensemble to have low classification error on random benign examples while simultaneously minimizing agreement on examples outside the training distribution.
We evaluate on both MNIST and CIFAR-10, against oblivious and both white- and black-box adversaries.

Training Ensembles to Detect Adversarial Examples · Around

Built on

Ensemble learning via negative correlation
Yong Liu and Xin Yao · 1999
Earlier work this paper cites.
Taxonomy for characterizing ensemble methods in classification tasks: A review and annotated bibliography
Lior Rokach · 2009
Earlier work this paper cites.
Intriguing properties of neural networks
Original
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus · 2013
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Original
Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy · 2014
Earlier work this paper cites.

Similar

Adversarial examples in the physical world
Original
Alexey Kurakin, Ian Goodfellow, and Samy Bengio · 2016
Cited alongside, same era.
Deepfool: a simple and accurate method to fool deep neural networks
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard · 2016
Cited alongside, same era.
Adversarial examples are not easily detected: Bypassing ten detection methods
Original
Nicholas Carlini and David Wagner · 2017
Cited alongside, same era.

Then

Towards evaluating the robustness of neural networks
Nicholas Carlini and David Wagner · 2017
Closest in time.
TensorFlow Tutorials: Convolutional Neural Networks
TensorFlow Contributors · 2017
Closest in time.
Adversarial example defenses: Ensembles of weak defenses are not strong
Original
Warren He, James Wei, Xinyun Chen, Nicholas Carlini, and Dawn Song · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…