arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.00255cs.CRcs.CV
收藏

面向深度模型交易的可撤销后门

Revocable Backdoor for Deep Model Trading

Fudan University(复旦大学)

Yiran Xu, Nan Zhong, Zhenxing Qian, Xinpeng Zhang

AI总结:

本文提出可撤销后门机制,通过掩码矩阵在不降低模型性能的情况下植入后门,并可在交易完成后无需重训练即可撤销,从而支持深度模型试用与交易场景。

摘要:

深度模型正被应用于众多领域,并已成为一种新的重要数字产品。与此同时,此前的研究表明,深度模型容易受到后门攻击,被攻陷的模型在触发样本出现时会返回攻击者期望的结果。后门攻击严重破坏了深度模型的可信性。在本文中,我们将深度模型的这一弱点转化为优势,并提出了一种新颖的可撤销后门以及深度模型交易场景。具体而言,我们的目标是在不降低模型性能的情况下攻陷深度模型,同时无需重新训练模型即可轻松对中毒模型进行解毒。我们设计了特定的掩码矩阵来管理模型的内部特征图,这些掩码矩阵可用于停用后门。可撤销后门可以应用于深度模型交易场景中:卖家训练带有可撤销后门的模型作为试用版本;买家向卖家支付押金并获得深度模型的试用版本;如果买家对试用版本满意,则向卖家支付尾款,卖家向买家发送掩码矩阵以撤销可撤销后门。我们通过多种数据集和网络架构验证了所提可撤销后门的可行性与鲁棒性。

英文摘要:

Deep models are being applied in numerous fields and have become a new important digital product. Meanwhile, previous studies have shown that deep models are vulnerable to backdoor attacks, in which compromised models return attacker-desired results when a trigger appears. Backdoor attacks severely break the trust-worthiness of deep models. In this paper, we turn this weakness of deep models into a strength, and propose a novel revocable backdoor and deep model trading scenario. Specifically, we aim to compromise deep models without degrading their performance, meanwhile, we can easily detoxify poisoned models without re-training the models. We design specific mask matrices to manage the internal feature maps of the models. These mask matrices can be used to deactivate the backdoors. The revocable backdoor can be adopted in the deep model trading scenario. Sellers train models with revocable backdoors as a trial version. Buyers pay a deposit to sellers and obtain a trial version of the deep model. If buyers are satisfied with the trial version, they pay a final payment to sellers and sellers send mask matrices to buyers to withdraw revocable backdoors. We demonstrate the feasibility and robustness of our revocable backdoor by various datasets and network architectures.

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。

↑