Skip to main content

Defending neural backdoors via generative distribution modeling

Publication ,  Conference
Qiao, X; Yang, Y; Li, H
Published in: Advances in Neural Information Processing Systems
January 1, 2019

Neural backdoor attack is emerging as a severe security threat to deep learning, while the capability of existing defense methods is limited, especially for complex backdoor triggers. In the work, we explore the space formed by the pixel values of all possible backdoor triggers. An original trigger used by an attacker to build the backdoored model represents only a point in the space. It then will be generalized into a distribution of valid triggers, all of which can influence the backdoored model. Thus, previous methods that model only one point of the trigger distribution is not sufficient. Getting the entire trigger distribution, e.g., via generative modeling, is a key of effective defense. However, existing generative modeling techniques for image generation are not applicable to the backdoor scenario as the trigger distribution is completely unknown. In this work, we propose max-entropy staircase approximator (MESA) for high-dimensional sampling-free generative modeling and use it to recover the trigger distribution. We also develop a defense technique to remove the triggers from the backdoored model. Our experiments on Cifar10/100 dataset demonstrate the effectiveness of MESA in modeling the trigger distribution and the robustness of the proposed defense method.

Duke Scholars

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Qiao, X., Yang, Y., & Li, H. (2019). Defending neural backdoors via generative distribution modeling. In Advances in Neural Information Processing Systems (Vol. 32).
Qiao, X., Y. Yang, and H. Li. “Defending neural backdoors via generative distribution modeling.” In Advances in Neural Information Processing Systems, Vol. 32, 2019.
Qiao X, Yang Y, Li H. Defending neural backdoors via generative distribution modeling. In: Advances in Neural Information Processing Systems. 2019.
Qiao, X., et al. “Defending neural backdoors via generative distribution modeling.” Advances in Neural Information Processing Systems, vol. 32, 2019.
Qiao X, Yang Y, Li H. Defending neural backdoors via generative distribution modeling. Advances in Neural Information Processing Systems. 2019.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology