2017

Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation

Yoo, YoungJoon, Park, Seonguk, Choi, Junyoung et al.

Understand

This paper proposes a new algorithm for controlling classification results by generating a small additive perturbation without changing the classifier network.

Our work is inspired by existing works generating adversarial perturbation that worsens classification performance.
In contrast to the existing methods, our work aims to generate perturbations that can enhance overall classification performance.
To solve this performance enhancement problem, we newly propose a perturbation generation network (PGN) influenced by the adversarial learning strategy.

Built on

Backpropagation applied to handwritten zip code recognition
Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel · 1989
Earlier work this paper cites.
An analysis of single-layer networks in unsupervised feature learning
A. Coates, A. Ng, and H. Lee · 2011
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.
Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
T. Tieleman and G. Hinton · 2012
Earlier work this paper cites.
Evasion attacks against machine learning at test time
B. Biggio, I. Corona, D. Maiorca, B. Nelson, N. Šrndić, P. Laskov, G. Giacinto, and F. Roli · 2013
Earlier work this paper cites.
Intriguing properties of neural networks
Original
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus · 2013
Earlier work this paper cites.
Generative adversarial nets
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio · 2014
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Original
I. J. Goodfellow, J. Shlens, and C. Szegedy · 2014
Earlier work this paper cites.
Towards deep neural network architectures robust to adversarial examples
Original
S. Gu and L. Rigazio · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
D. Kingma and J. Ba · 2014
Earlier work this paper cites.
Very deep convolutional networks for large-scale image recognition
Original
K. Simonyan and A. Zisserman · 2014
Earlier work this paper cites.
Analysis of classifiers’ robustness to adversarial perturbations
Original
A. Fawzi, O. Fawzi, and P. Frossard · 2015
Earlier work this paper cites.
Fast r-cnn
R. Girshick · 2015
Earlier work this paper cites.
Fully convolutional networks for semantic segmentation
J. Long, E. Shelhamer, and T. Darrell · 2015
Earlier work this paper cites.
Deepdream-a code example for visualizing neural networks
A. Mordvintsev, C. Olah, and M. Tyka · 2015
Earlier work this paper cites.
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
A. Nguyen, J. Yosinski, and J. Clune · 2015
Earlier work this paper cites.
Learning deconvolution network for semantic segmentation
H. Noh, S. Hong, and B. Han · 2015
Earlier work this paper cites.

Similar

Unsupervised representation learning with deep convolutional generative adversarial networks
Original
A. Radford, L. Metz, and S. Chintala · 2015
Cited alongside, same era.
Faster r-cnn: Towards real-time object detection with region proposal networks
S. Ren, K. He, R. Girshick, and J. Sun · 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, et al · 2015
Cited alongside, same era.
Adversarial manipulation of deep representations
Original
S. Sabour, Y. Cao, F. Faghri, and D. J. Fleet · 2015
Cited alongside, same era.
Going deeper with convolutions
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich · 2015
Cited alongside, same era.
Measuring neural net robustness with constraints
O. Bastani, Y. Ioannou, L. Lampropoulos, D. Vytiniotis, A. Nori, and A. Criminisi · 2016
Cited alongside, same era.
Robustness of classifiers: from adversarial to random noise
A. Fawzi, S.-M. Moosavi-Dezfooli, 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.
Densely connected convolutional networks
Original
G. Huang, Z. Liu, K. Q. Weinberger, and L. van der Maaten · 2016
Cited alongside, same era.
Delving into transferable adversarial examples and black-box attacks
Original
Y. Liu, X. Chen, C. Liu, and D. Song · 2016
Cited alongside, same era.
Least squares generative adversarial networks
Original
X. Mao, Q. Li, H. Xie, R. Y. Lau, Z. Wang, and S. P. Smolley · 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
Cited alongside, same era.

Then

Adversarial transformation networks: Learning to generate adversarial examples
Original
S. Baluja and I. Fischer · 2017
Closest in time.
Adversarial examples, uncertainty, and transfer testing robustness in gaussian process hybrid deep networks
Original
J. Bradshaw, A. G. d. G. Matthews, and Z. Ghahramani · 2017
Closest in time.
Keeping the bad guys out: Protecting and vaccinating deep learning with jpeg compression
Original
N. Das, M. Shanbhogue, S.-T. Chen, F. Hohman, L. Chen, M. E. Kounavis, and D. H. Chau · 2017
Closest in time.
Machine learning as an adversarial service: Learning black-box adversarial examples
Original
J. Hayes and G. Danezis · 2017
Closest in time.
Blocking transferability of adversarial examples in black-box learning systems
Original
H. Hosseini, Y. Chen, S. Kannan, B. Zhang, and R. Poovendran · 2017
Closest in time.
Safetynet: Detecting and rejecting adversarial examples robustly
Original
J. Lu, T. Issaranon, and D. Forsyth · 2017
Closest in time.
No need to worry about adversarial examples in object detection in autonomous vehicles
Original
J. Lu, H. Sibai, E. Fabry, and D. Forsyth · 2017
Closest in time.
On detecting adversarial perturbations
Original
J. H. Metzen, T. Genewein, V. Fischer, and B. Bischoff · 2017
Closest in time.
Universal adversarial perturbations
S.-M. Moosavi-Dezfooli, A. Fawzi, O. Fawzi, and P. Frossard · 2017
Closest in time.
Analysis of universal adversarial perturbations
Original
S.-M. Moosavi-Dezfooli, A. Fawzi, O. Fawzi, P. Frossard, and S. Soatto · 2017
Closest in time.
Fast feature fool: A data independent approach to universal adversarial perturbations
Original
K. R. Mopuri, U. Garg, and R. V. Babu · 2017
Closest in time.
Adversarial image perturbation for privacy protection–a game theory perspective
Original
S. J. Oh, M. Fritz, and B. Schiele · 2017
Closest in time.
Towards a visual privacy advisor: Understanding and predicting privacy risks in images
Original
T. Orekondy, B. Schiele, and M. Fritz · 2017
Closest in time.
Inception-v4, inception-resnet and the impact of residual connections on learning
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi · 2017
Closest in time.
Adversarial examples for semantic segmentation and object detection
Original
C. Xie, J. Wang, Z. Zhang, Y. Zhou, L. Xie, and A. Yuille · 2017
Closest in time.
Efficient defenses against adversarial attacks
Original
V. Zantedeschi, M.-I. Nicolae, and A. Rawat · 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…

Reading the bibliography…