arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.08602cs.CRcs.AI
收藏

通过通用对抗扰动对深度神经网络进行全局指纹识别

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations

Shanghai Jiao Tong University(上海交通大学);The Ohio State University(俄亥俄州立大学);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61);The University of Adelaide(阿德莱德大学)

Zirui Peng, Shaofeng Li, Guoxing Chen, Cheng Zhang, Haojin Zhu, Minhui Xue

摘要:

在本文中,我们提出了一种新的和实用的机制,使服务提供商,以验证是否嫌疑人模型是从受害者模型通过模型窃取攻击被盗。我们的关键见解是,DNN模型的决策边界的轮廓可以通过其通用对抗扰动(UAP)来唯一表征。非盗版模型属于低维子空间,盗版模型的子空间与受害者模型的子空间比非盗版模型的子空间更加一致。在此基础上,提出了一种面向DNN模型的UAP指纹识别方法,并通过对比学习对编码器进行训练,以指纹作为输入,输出一个相似度得分。广泛的研究表明,我们的框架可以检测模型IP违规,置信度> 99.99,只有20个指纹的可疑模型。它在不同的模型架构之间具有良好的通用性,并且对被盗模型的后期修改具有鲁棒性。

英文摘要:

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99 within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.

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。

↑