SecureRouter: Encrypted Routing for Efficient Secure Inference

Computer Science > Cryptography and Security [Submitted on 16 Apr 2026] SecureRouter: Encrypted Routing for Efficient Secure Inference Yukuan Zhang, Mengxin Zheng, Qian Lou Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior privacy-preserving inference systems co-design network optimizations with MPC, they remain slow and costly, limiting real-world deployment. A major bottleneck is their use of a single, fixed transformer model for all encrypted inputs, ignoring that different inputs require different model sizes to balance efficiency and accuracy. We present SecureRouter, an end-to-end encrypted routing and inference framework that accelerates secure transformer inference through input-adaptive model selection under encryption. SecureRouter establishes a unified encrypted pipeline that integrates a secure router with an MPC-optimized model pool, enabling coordinated routing, inference, and protocol execution while preserving full data and model confidentiality. The framework includes training-phase and inference-phase components: an MPC-cost-aware secure router that predicts per-model utility and cost from encrypted features, and an MPC-optimized model pool whose architectures and quantization schemes are co-trained to minimize MPC communication and computation overhead. Compared to prior work, SecureRouter achieves a latency reduction by 1.95x with negligible accuracy loss, offering a practical path toward scalable and efficient secure AI inference. Our open-source implementation is available at: this https URL Comments: To appear in the 63rd IEEE/ACM Design Automation Conference (DAC 2026) Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.15499 [cs.CR]   (or arXiv:2604.15499v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.15499 Focus to learn more Submission history From: Yukuan Zhang [view email] [v1] Thu, 16 Apr 2026 20:18:12 UTC (622 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)