MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense

@inproceedings{Sengupta2018MTDeepBT,
  title={MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense},
  author={Sailik Sengupta and Tathagata Chakraborti and Subbarao Kambhampati},
  booktitle={AAAI Workshops},
  year={2018}
}
Recent works on gradient based attacks and universal perturbations can adversarially modify images to bring down the accuracy of state-of-the-art classification techniques based on deep neural networks to as low as 10% on popular datasets like MNIST and ImageNet. The design of general defense strategies against a wide range of such attacks remains a challenging problem. In this paper, we derive inspiration from recent advances in the fields of cybersecurity and multi-agent systems and propose… CONTINUE READING
Tweets
This paper has been referenced on Twitter 7 times. VIEW TWEETS

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

A game theoretic approach to strategy generation for moving target defense in web applications. AAMAS

  • Sengupta
  • 2017

2016a. The limitations of deep learning in adversarial settings

  • Papernot
  • In Security and Privacy (EuroS&P),
  • 2016

Similar Papers

Loading similar papers…