Fetching the paper…

Reading the bibliography…

2017

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Behzadan, Vahid, Munir, Arslan

Original
PDF
Post on X

Understand

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples.

In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs) are also vulnerable to adversarial input perturbations, and verify the transferability of adversarial examples across different DQN models.
Furthermore, we present a novel class of attacks based on this vulnerability that enable policy manipulation and induction in the learning process of DQNs.
We propose an attack mechanism that exploits the transferability of adversarial examples to implement policy induction attacks on DQNs, and demonstrate its efficacy and impact through experimental study of a game-learning scenario.

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks · Around

Built on

R. S. Sutton, A. G. Barto, and R. J. Williams, “Reinforcement learning is direct adaptive optimal control,” IEEE Control Systems
1992
Earlier work this paper cites.
MIT Press Cambridge, 1998
R. S. Sutton and A. G. Barto, Introduction to reinforcement learning · 1998
Earlier work this paper cites.
L. Baird and A. W. Moore, “Gradient descent for general reinforcement learning,” Advances in neural information processing systems
1999
Earlier work this paper cites.
I. Ghory, “Reinforcement learning in board games,” Department of Computer Science, University of Bristol, Tech. Rep
2004
Earlier work this paper cites.
X. Dai, C.-K. Li, and A. B. Rad, “An approach to tune fuzzy controllers based on reinforcement learning for autonomous vehicle control,” IEEE Transactions on Intelligent Transportation Systems
2005
Earlier work this paper cites.
Apress, 2007
W. McGugan, Beginning game development with Python and Pygame: from novice to professional · 2007
Earlier work this paper cites.
L. Busoniu, R. Babuska, and B. De Schutter, “A comprehensive survey of multiagent reinforcement learning,” IEEE Transactions on Systems, Man, And Cybernetics-Part C: Applications and Reviews, 38 (2), 2008
2008
Earlier work this paper cites.
Y. Gao, J. Peters, A. Tsourdos, S. Zhifei, and E. Meng Joo, “A survey of inverse reinforcement learning techniques,” International Journal of Intelligent Computing and Cybernetics
2012
Earlier work this paper cites.

Similar

V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602
Original
2013
Cited alongside, same era.
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” arXiv preprint arXiv:1312.6199
Original
2013
Cited alongside, same era.
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” arXiv preprint arXiv:1412.6572
Original
2014
Cited alongside, same era.
V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, et al
2015
Cited alongside, same era.
T. Zhang, G. Kahn, S. Levine, and P. Abbeel, “Learning deep control policies for autonomous aerial vehicles with mpc-guided policy search,” arXiv preprint arXiv:1509.06791

Then

S. Gu, E. Holly, T. Lillicrap, and S. Levine, “Deep reinforcement learning for robotic manipulation,” arXiv preprint arXiv:1610.00633
Original
2016
Later among the works it cites.
A. Hussein, M. M. Gaber, and E. Elyan, “Deep active learning for autonomous navigation,” in International Conference on Engineering Applications of Neural Networks
2016
Later among the works it cites.
N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik, and A. Swami, “The limitations of deep learning in adversarial settings,” in 2016 IEEE European Symposium on Security and Privacy (EuroS&P)
2016
Later among the works it cites.
N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” arXiv preprint arXiv:1608.04644
Original
2016
Later among the works it cites.
N. Papernot, P. McDaniel, I. Goodfellow, S. Jha, Z. Berkay Celik, and A. Swami, “Practical black-box attacks against deep learning systems using adversarial examples,” arXiv preprint arXiv:1602.02697

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…

2015

Cited alongside, same era.

N. Papernot, P. McDaniel, X. Wu, S. Jha, and A. Swami, “Distillation as a defense to adversarial perturbations against deep neural networks,” arXiv preprint arXiv:1511.04508

2015

Cited alongside, same era.

M. Gilani, C. Inibhunu, and Q. H. Mahmoud, “Application and network performance of amazon elastic compute cloud instances,” in Cloud Networking (CloudNet), 2015 IEEE 4th International Conference on

2015

Cited alongside, same era.

2016

Later among the works it cites.

M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, et al

2016

Later among the works it cites.

N. Carlini and D. Wagner, “Defensive distillation is not robust to adversarial examples,” arXiv preprint

2016

Later among the works it cites.