Learn to Reverse DNNs from AI Programs Automatically

Simin Chen; Hamed Khanpour; Cong Liu; Wei Yang

IJCAI 2022poster17 citations

Learn to Reverse DNNs from AI Programs Automatically

Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang

Abstract

With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern. To quantify the model leakage risk of on-device DNNs automatically, we propose NNReverse, the first learning-based method which can reverse DNNs from AI programs without domain knowledge. NNReverse trains a representation model to represent the semantics of binary code for DNN layers. By searching the most similar function in our database, NNReverse infers the layer type of a given function’s binary code. To represent assembly instructions semantics precisely, NNReverse proposes a more fine-grained embedding model to represent the textual and structural-semantic of assembly functions.

AI Ethics, Trust, Fairness: Trustworthy AINatural Language Processing: EmbeddingsAI Ethics, Trust, Fairness: Societal Impact of AI

BibTeX

@inproceedings{ijcai2022p94,
  title     = {Learn to Reverse DNNs from AI Programs Automatically},
  author    = {Chen, Simin and Khanpour, Hamed and Liu, Cong and Yang, Wei},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {666--672},
  year      = {2022},
  month     = {7},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2022/94},
  url       = {https://doi.org/10.24963/ijcai.2022/94},
}