arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02450cs.LGcs.CRstat.ML
收藏

用秘密密钥训练DNN模型保护

Training DNN Model with Secret Key for Model Protection

Tokyo Metropolitan University(东京都立大学)

MaungMaung AprilPyone, Hitoshi Kiya

摘要:

在本文中,我们提出了一个模型保护方法,使用块式像素洗牌与秘密密钥作为预处理技术,以输入图像的第一次。受保护的模型是通过使用这种预处理的图像进行训练来构建的。实验结果表明,在密钥正确的情况下,保护模型的性能接近未保护模型,而在密钥错误的情况下,保护模型的性能严重下降;在保持与未保护模型几乎相同的性能精度的同时,该模型保护不仅对蛮干攻击具有鲁棒性,而且对微调攻击也具有鲁棒性.

英文摘要:

In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed images. Experiment results show that the performance of the protected model is close to that of non-protected models when the key is correct, while the accuracy is severely dropped when an incorrect key is given, and the proposed model protection is robust against not only brute-force attacks but also fine-tuning attacks, while maintaining almost the same performance accuracy as that of using a non-protected model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑