arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.01217cs.CRcs.LG
收藏

Unlearnable Clusters:面向标签无关的不可学习示例

Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

Beijing Jiaotong University(北京交通大学);Fudan University(复旦大学);Chinese Academy of Sciences(中国科学院);Peng Cheng Lab(鹏城实验室)

Jiaming Zhang, Xingjun Ma, Qi Yi, Jitao Sang, Yu-Gang Jiang, Yaowei Wang, Changsheng Xu

摘要:

人们对开发不可学习的示例(UE)来防止互联网上的视觉隐私泄露越来越感兴趣。UE是添加了不可见但不可学习的噪声的训练样本,已经发现其可以防止机器学习模型的未授权训练。UE通常经由具有代理模型的双层优化框架来生成,以从原始样本中移除(最小化)误差,然后应用于保护数据免受未知目标模型的影响。然而,现有的UE生成方法都依赖于称为标签一致性的理想假设,其中假设黑客和保护者对于给定样本持有相同的标签。在这项工作中,我们提出并推广了一个更实用的标签不可知设置,黑客可以利用受保护的数据完全不同的保护者。例如,在一个示例中,由保护者持有的M类不可学习数据集可能被黑客利用为N类数据集。现有的UE生成方法在这种具有挑战性的设置中变得无效。为了解决这一挑战,我们提出了一种新的技术,称为不可学习集群(UC)生成标签不可知的不可学习的例子与集群的扰动。此外,我们建议利用视觉和语言预训练模型(VLPM),如CLIP作为代理模型,以提高制作的UC到不同领域的可移植性。我们在不同的数据集,目标模型,甚至商业平台Microsoft Azure和Baidu PaddlePaddle的各种设置下实证验证了我们提出的方法的有效性。代码可在\url{https://github.com/jiamingzhang94/Unlearnable-Clusters}上获得。

英文摘要:

There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noise, which have been found can prevent unauthorized training of machine learning models. UEs typically are generated via a bilevel optimization framework with a surrogate model to remove (minimize) errors from the original samples, and then applied to protect the data against unknown target models. However, existing UE generation methods all rely on an ideal assumption called label-consistency, where the hackers and protectors are assumed to hold the same label for a given sample. In this work, we propose and promote a more practical label-agnostic setting, where the hackers may exploit the protected data quite differently from the protectors. E.g., a m-class unlearnable dataset held by the protector may be exploited by the hacker as a n-class dataset. Existing UE generation methods are rendered ineffective in this challenging setting. To tackle this challenge, we present a novel technique called Unlearnable Clusters (UCs) to generate label-agnostic unlearnable examples with cluster-wise perturbations. Furthermore, we propose to leverage VisionandLanguage Pre-trained Models (VLPMs) like CLIP as the surrogate model to improve the transferability of the crafted UCs to diverse domains. We empirically verify the effectiveness of our proposed approach under a variety of settings with different datasets, target models, and even commercial platforms Microsoft Azure and Baidu PaddlePaddle. Code is available at \url{https://github.com/jiamingzhang94/Unlearnable-Clusters}.

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。

↑