Caiqin Dong (Jinan University), Jian Weng (Jinan University), Jia-Nan Liu (Jinan University), Yue Zhang (Jinan University), Yao Tong (Guangzhou Fongwell Data Limited Company), Anjia Yang (Jinan University), Yudan Cheng (Jinan University), Shun Hu (Jinan University)

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.

View More Papers

Anomaly Detection in the Open World: Normality Shift Detection,...

Dongqi Han (Tsinghua University), Zhiliang Wang (Tsinghua University), Wenqi Chen (Tsinghua University), Kai Wang (Tsinghua University), Rui Yu (Tsinghua University),...

Read More

Are some prices more equal than others? Evaluating store-based...

Hugo Jonker (Open University Netherlands), Stefan Karsch (TH Koln), Benjamin Krumnow (TH Koln), Godfried Meesters (Open University Netherlands)

Read More

ChargePrint: A Framework for Internet-Scale Discovery and Security Analysis...

Tony Nasr (Concordia University), Sadegh Torabi (George Mason University), Elias Bou-Harb (University of Texas at San Antonio), Claude Fachkha (University...

Read More

Automata-Based Automated Detection of State Machine Bugs in Protocol...

Paul Fiterau-Brostean (Uppsala University, Sweden), Bengt Jonsson (Uppsala University, Sweden), Konstantinos Sagonas (Uppsala University, Sweden and National Technical University of...

Read More