Pith. sign in

REVIEW 6 cited by

MPCFormer: fast, performant and private Transformer inference with MPC

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.01452 v2 pith:MMSQL5FS submitted 2022-11-02 cs.LG cs.CR

Dacheng Li , Rulin Shao , Hongyi Wang , Han Guo , Eric P. Xing , Hao Zhang This is my paper
classification cs.LGcs.CR
keywords inferencempcformertransformerperformanceprivateachievesbertbasemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Enabling private inference is crucial for many cloud inference services that are based on Transformer models. However, existing private inference solutions can increase the inference latency by more than 60x or significantly compromise the inference quality. In this paper, we design the framework MPCFORMER as a practical solution, using Secure Multi-Party Computation (MPC) and Knowledge Distillation (KD). Through extensive evaluations, we show that MPCFORMER significantly speeds up Transformer inference in MPC settings while achieving similar ML performance to the input model. On the IMDb dataset, it achieves similar performance to BERTBASE, while being 5.3x faster. On the GLUE benchmark, it achieves 97% performance of BERTBASE with a 2.2x speedup. MPCFORMER remains effective with different trained Transformer weights such as ROBERTABASE and larger models including BERTLarge. Code is available at https://github.com/MccRee177/MPCFormer.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Private Vertical Federated Inference for Time-Series

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    PPHH-VFL splits the model head into a plaintext public part secured by adversarial training and a small MPC private part, yielding up to 6 orders of magnitude faster inference than end-to-end MPC on models up to 86M p...

  2. CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation

    cs.CR 2025-11 conditional novelty 6.0 of 10

    An MPC-ML compiler that modularizes and auto-tunes operator approximations, delivering 1.2–1.8x speedups over an optimized baseline under user-set accuracy bounds.

  3. ENSI: Efficient Non-Interactive Secure Inference for Large Language Models

    cs.CR 2025-09 conditional novelty 6.0 of 10

    ENSI performs secure, non-interactive LLM inference by co-designing CKKS homomorphic encryption with BitNet's ternary weights, achieving up to 8x faster matrix multiplication and 2.6x faster softmax than prior work.

  4. Token Economics for LLM Agents: A Dual-View Study from Computing and Economics

    cs.AI 2026-05 unverdicted novelty 4.0 of 10

    The paper delivers a unified survey of token economics for LLM agents, conceptualizing tokens as production factors, exchange mediums, and units of account across micro, meso, macro, and security dimensions using esta...

  5. Private, Verifiable, and Auditable AI Systems

    cs.CR 2025-08 conditional novelty 4.0 of 10

    A thesis demonstrating partial prototypes for zk-verifiable model evaluation and privacy-preserving retrieval, and arguing these pieces can compose into end-to-end auditable AI systems.

  6. Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives

    cs.CR 2025-07 conditional novelty 4.0 of 10

    A structured survey of PPML efficiency optimizations, grouped into protocol, model, and system levels, with comparisons and future directions.

Pith tools