Skip to main content

2017 | OriginalPaper | Buchkapitel

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

verfasst von : Vahid Behzadan, Arslan Munir

Erschienen in: Machine Learning and Data Mining in Pattern Recognition

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

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.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998) Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)
2.
Zurück zum Zitat Ghory, I.: Reinforcement learning in board games, Department of Computer Science, University of Bristol. Technical report (2004) Ghory, I.: Reinforcement learning in board games, Department of Computer Science, University of Bristol. Technical report (2004)
3.
Zurück zum Zitat Dai, X., Li, C.-K., Rad, A.B.: An approach to tune fuzzy controllers based on reinforcement learning for autonomous vehicle control. IEEE Trans. Intell. Transp. Syst. 6(3), 285–293 (2005)CrossRef Dai, X., Li, C.-K., Rad, A.B.: An approach to tune fuzzy controllers based on reinforcement learning for autonomous vehicle control. IEEE Trans. Intell. Transp. Syst. 6(3), 285–293 (2005)CrossRef
4.
Zurück zum Zitat Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 38(2), 156 (2008)CrossRef Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 38(2), 156 (2008)CrossRef
5.
Zurück zum Zitat Sutton, R.S., Barto, A.G., Williams, R.J.: Reinforcement learning is direct adaptive optimal control. IEEE Control Syst. 12(2), 19–22 (1992)CrossRef Sutton, R.S., Barto, A.G., Williams, R.J.: Reinforcement learning is direct adaptive optimal control. IEEE Control Syst. 12(2), 19–22 (1992)CrossRef
6.
Zurück zum Zitat Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013) Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:​1312.​5602 (2013)
7.
Zurück zum Zitat Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRef Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRef
8.
Zurück zum Zitat Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation. arXiv preprint arXiv:1610.00633 (2016) Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation. arXiv preprint arXiv:​1610.​00633 (2016)
9.
Zurück zum Zitat Zhang, T., Kahn, G., Levine, S., Abbeel, P.: Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search. arXiv preprint arXiv:1509.06791 (2015) Zhang, T., Kahn, G., Levine, S., Abbeel, P.: Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search. arXiv preprint arXiv:​1509.​06791 (2015)
10.
11.
Zurück zum Zitat Baird, L., Moore, A.W.: Gradient descent for general reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 968–974 (1999) Baird, L., Moore, A.W.: Gradient descent for general reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 968–974 (1999)
12.
Zurück zum Zitat McGugan, W.: Beginning game development with Python and Pygame: from novice to professional. Apress (2007) McGugan, W.: Beginning game development with Python and Pygame: from novice to professional. Apress (2007)
13.
Zurück zum Zitat Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016) Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)
14.
Zurück zum Zitat Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. arXiv preprint arXiv:1511.04508 (2015) Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. arXiv preprint arXiv:​1511.​04508 (2015)
15.
16.
Zurück zum Zitat Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013) Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks. arXiv preprint arXiv:​1312.​6199 (2013)
17.
Zurück zum Zitat Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014) Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:​1412.​6572 (2014)
18.
Zurück zum Zitat Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against deep learning systems using adversarial examples. arXiv preprint arXiv:1602.02697 (2016) Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against deep learning systems using adversarial examples. arXiv preprint arXiv:​1602.​02697 (2016)
19.
Zurück zum Zitat Gao, Y., Peters, J., Tsourdos, A., Zhifei, S., Joo, E.M.: A survey of inverse reinforcement learning techniques. Int. J. Intell. Comput. Cybern. 5(3), 293–311 (2012)MathSciNetCrossRef Gao, Y., Peters, J., Tsourdos, A., Zhifei, S., Joo, E.M.: A survey of inverse reinforcement learning techniques. Int. J. Intell. Comput. Cybern. 5(3), 293–311 (2012)MathSciNetCrossRef
20.
Zurück zum Zitat Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016) Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:​1603.​04467 (2016)
21.
Zurück zum Zitat Gilani, M., Inibhunu, C., Mahmoud, Q.H.: Application and network performance of Amazon elastic compute cloud instances. In: 2015 IEEE 4th International Conference on Cloud Networking (CloudNet), pp. 315–318. IEEE (2015) Gilani, M., Inibhunu, C., Mahmoud, Q.H.: Application and network performance of Amazon elastic compute cloud instances. In: 2015 IEEE 4th International Conference on Cloud Networking (CloudNet), pp. 315–318. IEEE (2015)
22.
Zurück zum Zitat Carlini, N., Wagner, D.: Defensive distillation is not robust to adversarial examples. arXiv preprint (2016) Carlini, N., Wagner, D.: Defensive distillation is not robust to adversarial examples. arXiv preprint (2016)
Metadaten
Titel
Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks
verfasst von
Vahid Behzadan
Arslan Munir
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-62416-7_19

Premium Partner