Newest papers

Interflow: Breaking the Offline-Online Barrier for Private AI at the Edge

Hanieh Totonchi Asl, Ebrahim Nouri, Zhuoran Li, Danella Zhao · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27431 · cited by 0 works (OpenAlex) · open-access PDF

Korean

개인 정보 보호를 통한 PCML(Privacy-preserving machine learning)는 민감한 사용자 데이터를 노출하지 않고도 강력한 AI 서비스를 가장자리에 전달하는 유망한 경로를 제공합니다. 그러나 실용적인 배포는 안전한 멀티 파티 컴퓨팅 (MPC)의 높은 통신, 계산 및 데이터 이동 비용에 의해 제한됩니다. 기존의 MPC 시스템은 일반적으로 온라인 실행에서 무작위 무작위 발생을 해제하여 온라인 실행에서 무작위 발생을 해제합니다. 또한, 제한된 저장비는 안전한 멀티 파티 컴퓨팅 (MPC) 실행 패턴을 강제 할 수 있습니다. 특히 비선형 추론 동안 파이프라인을 반복하여 파이프라인을 정지합니다. 기존의 MPC 시스템은 기본적인 경로에서 무작위

Machine translation (Meta M2M100); the English original follows.

Abstract

Privacy-preserving machine learning (PPML) offers a promising path toward bringing powerful AI services to the edge without exposing sensitive user data. However, its practical deployment remains constrained by the high communication, computation, and data-movement costs of secure multi-party computation (MPC), particularly during nonlinear inference. Existing MPC systems typically decouple input-independent correlated randomness generation from online execution, creating substantial memory pressure to buffer single-use cryptographic data. Moreover, limited storage can force a stop-and-refill execution pattern that repeatedly stalls the pipeline to replenish these buffers, bringing randomness generation back onto the critical path. We propose Interflow, an algorithm-hardware co-design that rethinks this separation by batch-wise processing and pipelining correlated-randomness generation with online execution: while the current batch consumes pre-generated randomness to execute secure nonlinear operations, correlation generation proceeds concurrently for the next batch. By leveraging interleaved execution, efficient data movement, and hardware acceleration, the design transforms preprocessing from a serialized, storage-intensive offline phase into a continuously overlapped pipeline that generates correlated randomness closer to the point of consumption, reducing memory footprint and data movement overhead. Implemented on the Zynq UltraScale+ ZCU102, Interflow improves nonlinear evaluation throughput by up to 1.55x for CNN operators and 1.48x for transformer operators. It achieves up to 1.26x speedup for ResNet-50 and up to 1.21x speedup for BERT-base, and reduces memory footprint by up to 37%, compared with baseline frameworks.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Speedup, Randomness, Pipeline (software), Memory footprint, Throughput

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange