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 2205.03040cs.CR
收藏

Fusion:可抵御恶意服务器的高效安全推理

Fusion: Efficient and Secure Inference Resilient to Malicious Servers

Caiqin Dong, Jian Weng, Jia-Nan Liu, Yue Zhang, Yao Tong, Anjia Yang, Yudan Cheng, Shun Hu

AI总结:

针对安全机器学习推理中恶意服务器可能偏离协议、使用低质量模型的问题,提出Fusion框架,通过混合公开样本与待查询样本的多方计算强制服务器诚实,在效率和通信开销上均优于现有方案。

摘要:

在安全机器学习推理领域,大多数方案均假设服务器是半诚实的(即诚实遵守协议,但试图推断额外信息)。然而在现实场景中,服务器可能是恶意的(例如使用低质量模型,或是偏离协议执行)。尽管已有少量研究考虑了偏离协议的恶意服务器场景,但这些研究均忽略了模型准确性验证(即恶意服务器使用低质量模型的情况),同时还需兼顾服务器模型与客户端输入的隐私保护。为解决上述问题,我们提出Fusion框架:客户端将已知查询结果的公开样本与自身待查询的样本混合,作为多方计算的输入,共同执行安全推理。由于使用低质量模型或偏离协议的服务器只能生成客户端可轻易识别的错误结果,Fusion能够强制服务器诚实行为,无需借助高开销的密码学技术即可解决所有前述问题。我们的评估结果显示,与现有的恶意安全推理协议(该协议目前不支持模型准确性验证)相比,Fusion的速度提升48.06倍,通信量降低30.90倍。此外,为验证其可扩展性,我们在实用的ResNet50模型上开展了ImageNet规模的推理实验,在广域网(WAN)环境下耗时8.678分钟,通信量为10.117 GiB,速度比半诚实协议快1.18倍,通信量比半诚实协议少2.64倍。

英文摘要:

In secure machine learning inference, most of the schemes assume that the server is semi-honest (honestly following the protocol but attempting to infer additional information). However, the server may be malicious (e.g., using a low-quality model or deviating from the protocol) in the real world. Although a few studies have considered a malicious server that deviates from the protocol, they ignore the verification of model accuracy (where the malicious server uses a low-quality model) meanwhile preserving the privacy of both the server's model and the client's inputs. To address these issues, we propose \textit{Fusion}, where the client mixes the public samples (which have known query results) with their own samples to be queried as the inputs of multi-party computation to jointly perform the secure inference. Since a server that uses a low-quality model or deviates from the protocol can only produce results that can be easily identified by the client, \textit{Fusion} forces the server to behave honestly, thereby addressing all those aforementioned issues without leveraging expensive cryptographic techniques. Our evaluation indicates that \textit{Fusion} is 48.06$\times$ faster and uses 30.90$\times$ less communication than the existing maliciously secure inference protocol (which currently does not support the verification of the model accuracy). In addition, to show the scalability, we conduct ImageNet-scale inference on the practical ResNet50 model and it costs 8.678 minutes and 10.117 GiB of communication in a WAN setting, which is 1.18$\times$ faster and has 2.64$\times$ less communication than those of the semi-honest protocol.

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。

↑