FLASH: Fast and Robust Framework for Privacy-preserving Machine Learning

TLDR

PPML via MPC has gained momentum, yet existing frameworks such as ABY3 and SecureNN rely on 3 parties and provide only abort‑based security. The authors propose FLASH, a four‑party PPML framework over ℤ₂^ℓ that guarantees output delivery regardless of adversary behavior. FLASH achieves real‑time efficiency with custom tools—a vector‑size‑independent dot product, constant‑round truncation and MSB extraction without heavy circuits, and supports secure server‑aided prediction for linear, logistic, deep, and binarized neural networks, all implemented over a 64‑bit ring in LAN and WAN. Benchmarks show FLASH outperforms ABY3, achieving throughput gains of 24× to 1390× on MNIST across LAN and WAN.

Abstract

Abstract Privacy-preserving machine learning (PPML) via Secure Multi-party Computation (MPC) has gained momentum in the recent past. Assuming a minimal network of pair-wise private channels, we propose an efficient four-party PPML framework over rings ℤ 2 ℓ, FLASH, the first of its kind in the regime of PPML framework, that achieves the strongest security notion of Guaranteed Output Delivery (all parties obtain the output irrespective of adversary’s behaviour). The state of the art ML frameworks such as ABY3 by Mohassel et.al (ACM CCS’18) and SecureNN by Wagh et.al (PETS’19) operate in the setting of 3 parties with one malicious corruption but achieve the weaker security guarantee of abort . We demonstrate PPML with real-time efficiency, using the following custom-made tools that overcome the limitations of the aforementioned state-of-the-art– (a) dot product , which is independent of the vector size unlike the state-of-the-art ABY3, SecureNN and ASTRA by Chaudhari et.al (ACM CCSW’19), all of which have linear dependence on the vector size. (b) Truncation and MSB Extraction , which are constant round and free of circuits like Parallel Prefix Adder (PPA) and Ripple Carry Adder (RCA), unlike ABY3 which uses these circuits and has round complexity of the order of depth of these circuits. We then exhibit the application of our FLASH framework in the secure server-aided prediction of vital algorithms– Linear Regression, Logistic Regression, Deep Neural Networks, and Binarized Neural Networks. We substantiate our theoretical claims through improvement in benchmarks of the aforementioned algorithms when compared with the current best framework ABY3. All the protocols are implemented over a 64-bit ring in LAN and WAN. Our experiments demonstrate that, for MNIST dataset, the improvement (in terms of throughput) ranges from 24 × to 1390 × over LAN and WAN together.