ML Anthology

Learn to Reverse DNNs from AI Programs Automatically

Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang
IJCAI 2022 pp. 666-672
doi:10.24963/IJCAI.2022/94 /ijcai/2022/chen2022ijcai-learn/

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.

PDF IJCAI Semantic Scholar

Cite

Text

Chen et al. "Learn to Reverse DNNs from AI Programs Automatically." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/94

Markdown

[Chen et al. "Learn to Reverse DNNs from AI Programs Automatically." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/chen2022ijcai-learn/) doi:10.24963/IJCAI.2022/94

BibTeX

@inproceedings{chen2022ijcai-learn,
  title     = {{Learn to Reverse DNNs from AI Programs Automatically}},
  author    = {Chen, Simin and Khanpour, Hamed and Liu, Cong and Yang, Wei},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {666-672},
  doi       = {10.24963/IJCAI.2022/94},
  url       = {https://mlanthology.org/ijcai/2022/chen2022ijcai-learn/}
}