2017

Geometric robustness of deep networks: analysis and improvement

Kanbak, Can, Moosavi-Dezfooli, Seyed-Mohsen, Frossard, Pascal

Understand

Deep convolutional neural networks have been shown to be vulnerable to arbitrary geometric transformations.

However, there is no systematic method to measure the invariance properties of deep networks to such transformations.
We propose ManiFool as a simple yet scalable algorithm to measure the invariance of deep networks.
In particular, our algorithm measures the robustness of deep networks to geometric transformations in a worst-case regime as they can be problematic for sensitive applications.

A fast marching level set method for monotonically advancing fronts
J. A. Sethian · 1996
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner · 1998
Earlier work this paper cites.
The multiscale structure of non-differentiable image manifolds
M. B. Wakin, D. L. Donoho, H. Choi, and R. G. Baraniuk · 2005
Earlier work this paper cites.
Optimization Algorithms on Matrix Manifolds
P.-A. Absil, R. Mahony, and R. Sepulchre · 2008
Earlier work this paper cites.
Measuring invariances in deep networks
I. Goodfellow, H. Lee, Q. V. Le, A. Saxe, and A. Y. Ng · 2009
Earlier work this paper cites.
Minimum Distance between Pattern Transformation Manifolds: Algorithm and Applications
E. Kokiopoulou and P. Frossard · 2009
Earlier work this paper cites.
Learning Multiple Layers of Features from Tiny Images
A. Krizhevsky and G. Hinton · 2009
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
A. Krizhevsky, I. Sutskever, and G. E. Hinton · 2012
Earlier work this paper cites.
Intriguing properties of neural networks
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus · 2014
Earlier work this paper cites.

Manitest: Are classifiers really invariant?
A. Fawzi and P. Frossard · 2015
Cited alongside, same era.
Explaining and harnessing adversarial examples
I. J. Goodfellow, J. Shlens, and C. Szegedy · 2015
Cited alongside, same era.
Spatial transformer networks
M. Jaderberg, K. Simonyan, A. Zisserman, and others · 2015
Cited alongside, same era.
Understanding image representations by measuring their equivariance and equivalence
K. Lenc and A. Vedaldi · 2015
Cited alongside, same era.
ImageNet Large Scale Visual Recognition Challenge
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei · 2015
Cited alongside, same era.
Very deep convolutional networks for large-scale image recognition
K. Simonyan and A. Zisserman · 2015
Cited alongside, same era.
Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
A. Bakry, M. Elhoseiny, T. El-Gaaly, and A. Elgammal · 2016
Cited alongside, same era.
Measuring the effect of nuisance variables on classifiers
A. Fawzi and P. Frossard · 2016
Cited alongside, same era.
Deep Residual Learning for Image Recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.

Deepfool: A simple and accurate method to fool deep neural networks
S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard · 2016
Later among the works it cites.
Adversarial Manipulation of Deep Representations
S. Sabour, Y. Cao, F. Faghri, and D. J. Fleet · 2016
Later among the works it cites.
Transform-Invariant Convolutional Neural Networks for Image Classification and Search
X. Shen, X. Tian, A. He, S. Sun, and D. Tao · 2016
Later among the works it cites.
Visual Representations: Defining Properties and Deep Approximations
S. Soatto and A. Chiuso · 2016
Later among the works it cites.
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
Original
S. Baluja and I. Fischer · 2017
Closest in time.
Towards evaluating the robustness of neural networks
N. Carlini and D. Wagner · 2017
Closest in time.
Deformable Convolutional Networks
J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, and Y. Wei · 2017
Closest in time.
Robust Physical-World Attacks on Deep Learning Models
Original
I. Evtimov, K. Eykholt, E. Fernandes, T. Kohno, B. Li, A. Prakash, A. Rahmati, and D. Song · 2017
Closest in time.
Differential Geometry
L. W. Tu · 2017
Closest in time.

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

alphaXiv is searching for related work…

Reading the bibliography…