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 2103.10021cs.CR
收藏

基于多任务学习的深度神经网络安全水印

Secure Watermark for Deep Neural Networks with Multi-task Learning

Fangqi Li, Shilin Wang

摘要:

深度神经网络在许多实际应用中发挥着重要作用。在用丰富的数据和计算资源训练后,提供服务的深度神经网络模型被赋予了经济价值。商业化和保护深度神经网络的一个重要前提是可靠地识别其真正的作者。为了实现这一目标,人们提出了将作者身份信息嵌入到网络中的水印方案。然而,目前的计划很难满足所有必要的要求,安全地证明作者,主要集中在模型的分类。为了明确地满足安全需求的形式化定义并增加深度神经网络水印方案的适用性,我们提出了一种基于多任务学习的新框架。通过将水印嵌入视为一项额外的任务,大多数安全要求都是明确制定的,并通过精心设计的正则化器来满足,其余的则通过使用密码学组件来保证。此外,一个分散的验证协议,提出了标准化的所有权验证。实验结果表明,该方案具有灵活性、安全性和鲁棒性,是深度学习模型保护的一种有效方案.

英文摘要:

Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important prerequisite in commercializing and protecting deep neural networks is the reliable identification of their genuine author. To meet this goal, watermarking schemes that embed the author's identity information into the networks have been proposed. However, current schemes can hardly meet all the necessary requirements for securely proving the authorship and mostly focus on models for classification. To explicitly meet the formal definitions of the security requirements and increase the applicability of deep neural network watermarking schemes, we propose a new framework based on multi-task learning. By treating the watermark embedding as an extra task, most of the security requirements are explicitly formulated and met with well-designed regularizers, the rest is guaranteed by using components from cryptography. Moreover, a decentralized verification protocol is proposed to standardize the ownership verification. The experiment results show that the proposed scheme is flexible, secure, and robust, hence a promising candidate in deep learning model protection.

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。

↑