论文标题

联邦调查局:带有良性输入的指纹模型

FBI: Fingerprinting models with Benign Inputs

论文作者

Maho, Thibault, Furon, Teddy, Merrer, Erwan Le

论文摘要

深神经网络的指纹识别的最新进展检测了放置在黑盒相互作用方案中的模型实例。指纹协议使用的输入是专门为检查的每个精确模型而设计的。尽管在这种情况下有效,但这仍然导致仅在模型的修改(例如重新训练,量化)之后缺乏保证。本文通过推广到模型家族及其变体的概念,ii)指纹构成的概念,ii)指纹识别的概念,ii)指纹识别任务的扩展,这些挑战具有弹性,这些方案具有对模型的重大修改,ii)ii)指纹识别任务的扩展,包括指纹的任务,包括一个人希望在其中识别指纹模型(以前识别一个模型),以确定指纹模型,以识别型号 - 以识别型号)。我们通过证明良性输入(例如未修改的图像)是两个任务的足够材料来实现这两个目标。我们利用信息理论方案来进行识别任务。我们为检测任务设计了一种贪婪的歧视算法。两种方法均在空前的1000多个网络中进行实验验证。

Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked for. While efficient in such a scenario, this nevertheless results in a lack of guarantee after a mere modification (like retraining, quantization) of a model. This paper tackles the challenges to propose i) fingerprinting schemes that are resilient to significant modifications of the models, by generalizing to the notion of model families and their variants, ii) an extension of the fingerprinting task encompassing scenarios where one wants to fingerprint not only a precise model (previously referred to as a detection task) but also to identify which model family is in the black-box (identification task). We achieve both goals by demonstrating that benign inputs, that are unmodified images, for instance, are sufficient material for both tasks. We leverage an information-theoretic scheme for the identification task. We devise a greedy discrimination algorithm for the detection task. Both approaches are experimentally validated over an unprecedented set of more than 1,000 networks.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源