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 2602.19918cs.CRcs.LG
收藏

RobPI: 面对恶意客户端的鲁棒隐私推断

RobPI: Robust Private Inference against Malicious Client

University of Central Florida(中央佛罗里达大学)

Jiaqi Xue, Mengxin Zheng, Qian Lou

AI总结:

RobPI是一种针对恶意客户端的鲁棒隐私推断协议,通过加密兼容噪声提升安全性,有效降低攻击成功率并增加攻击所需查询次数。

摘要:

机器学习推断在各种应用中的广泛部署引发了隐私担忧。为此,已创建隐私推断(PI)协议,使各方能够在不泄露敏感数据的情况下进行推断。尽管最近在PI效率方面取得了进展,但大多数当前方法假设半诚实威胁模型,其中数据拥有者诚实并遵守协议。然而,现实中数据拥有者可能有不同的动机并以不可预测的方式行动,使这一假设不切实际。为了展示恶意客户端如何破坏半诚实模型,我们首先设计了一种针对多种最新隐私推断协议的推断操纵攻击。这种攻击使恶意客户端能够以比当前黑盒攻击少3到8倍的查询次数修改模型输出。受这些攻击的启发,我们提出了并实现了RobPI,一种鲁棒且具有弹性的隐私推断协议,能够抵御恶意客户端。RobPI集成了一个独特的加密协议,通过将加密兼容的噪声编织到隐私推断的logits和特征中,从而高效地抵御恶意客户端攻击。我们对各种神经网络和数据集进行了广泛实验,结果表明RobPI将攻击成功率降低约91.9%,并使恶意客户端攻击所需的查询次数增加超过10倍。

英文摘要:

The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allow parties to perform inference without revealing their sensitive data. Despite recent advances in the efficiency of PI, most current methods assume a semi-honest threat model where the data owner is honest and adheres to the protocol. However, in reality, data owners can have different motivations and act in unpredictable ways, making this assumption unrealistic. To demonstrate how a malicious client can compromise the semi-honest model, we first designed an inference manipulation attack against a range of state-of-the-art private inference protocols. This attack allows a malicious client to modify the model output with 3x to 8x fewer queries than current black-box attacks. Motivated by the attacks, we proposed and implemented RobPI, a robust and resilient private inference protocol that withstands malicious clients. RobPI integrates a distinctive cryptographic protocol that bolsters security by weaving encryption-compatible noise into the logits and features of private inference, thereby efficiently warding off malicious-client attacks. Our extensive experiments on various neural networks and datasets show that RobPI achieves ~91.9% attack success rate reduction and increases more than 10x the number of queries required by malicious-client attacks.

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。

↑