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 1912.08987cs.LGcs.CRstat.ML
收藏

仅输入噪声的模型权重窃取:Petulant Attacker的奇怪案例

Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker

UnifyID AI Labs(UnifyID人工智能实验室)

Nicholas Roberts, Vinay Uday Prabhu, Matthew McAteer

摘要:

本文探讨了攻击者可以声称“噪声和对模型softmax层的访问是您所需要的”来窃取其架构已知的卷积神经网络的权重的场景。我们能够使用被盗的MNIST模型实现96%的测试准确率,使用仅使用i.i.d.学习的被盗KMNIST模型实现82%的准确率。伯努利噪声输入。我们认为这种权重的盗窃敏感性表明了数据集的复杂性,并提出了一个新的度量标准来捕获相同的信息。这种传播的目标不仅是展示在模型窃取方面了解架构可以让你走多远,而且还提请注意由i.i.d.激发的CNN的这种相当特殊的权重可学习性方面。噪声输入我们还传播了一些初步的结果与使用伊辛概率分布代替i.i.d.伯努利分布

英文摘要:

This paper explores the scenarios under which an attacker can claim that 'Noise and access to the softmax layer of the model is all you need' to steal the weights of a convolutional neural network whose architecture is already known. We were able to achieve 96% test accuracy using the stolen MNIST model and 82% accuracy using the stolen KMNIST model learned using only i.i.d. Bernoulli noise inputs. We posit that this theft-susceptibility of the weights is indicative of the complexity of the dataset and propose a new metric that captures the same. The goal of this dissemination is to not just showcase how far knowing the architecture can take you in terms of model stealing, but to also draw attention to this rather idiosyncratic weight learnability aspects of CNNs spurred by i.i.d. noise input. We also disseminate some initial results obtained with using the Ising probability distribution in lieu of the i.i.d. Bernoulli distribution.

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。

↑