Shuffled Transformers for Blind Training

Hengyuan Xu, Liyao Xiang, Hangyu Ye, Dixi Yao, Pengzhi Chu

Keywords: Data privacy, split learning, Transformer, privacy-preserving

Abstract: Conventional split learning faces the challenge of preserving training data and model privacy as a part of the training is beyond the data owner's control. We tackle this problem by introducing blind training, i.e., training without being aware of the data or the model, realized by shuffled Transformers. This is attributed to our intriguing findings that the inputs and the model weights of the Transformer encoder blocks, the backbone of Transformer, can be shuffled without degrading the model performance. We not only have proven the shuffling invariance property in theory, but also designs a privacy-preserving split learning framework following the property, with little modification to the original Transformer architecture. We carry out verification of the properties through experiments, and also show our proposed framework successfully defends privacy attacks to split learning with superiority.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)