mlsanityData to 14 Oct 2026

Private Vertical Federated Inference for Time-Series

arXiv 2605.08343 ↗First posted 8 May 2026cs.LG cs.CR cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Institutions may benefit from collaborative inference on time-series data. In settings where privacy is necessary, multi-party computation (MPC) is a straightforward approach to providing strong guarantees, yet it remains prohibitively expensive and scales poorly with modern transformer architectures. Vertical Federated Learning (VFL) offers efficiency but suffers from privacy leakage at the embedding level, and securing the entire VFL model head via MPC remains prohibitively slow and communication-heavy for larger models. To enable practical, secure inference at scale, we propose "Public/Private Hybrid Head-VFL" (PPHH-VFL). This hybrid architecture splits the model head into an efficient plaintext public head and a secure, lightweight MPC private head. By applying adversarial training to the public embeddings, we mitigate privacy leakage; concurrently, the small private head securely preserves the flow of sensitive information needed for high downstream utility. Empirical evaluations on models ranging up to 86 million parameters demonstrate that PPHH-VFL accelerates inference by up to six orders of magnitude compared to end-to-end MPC. Compared to a standard VFL+MPC baseline, our approach scales significantly better, achieving a speedup of up to 44.4x in WAN and a 91.2x reduction in communication costs (dropping from 1.7 GB to 19 MB per batch), while simultaneously improving downstream classification accuracy by 2.50% and regression RMSE by 40.7%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

23 of 37 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2018Robustness May Be at Odds with Accuracycited by 880
  5. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  6. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  7. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  8. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  9. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  10. 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
  11. 2019Overlearning Reveals Sensitive Attributescited by 76
  12. 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 69
11 more
  1. 2018AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learningcited by 60
  2. 2019Local Differential Privacy for Deep Learningcited by 46
  3. 2022Label Leakage and Protection from Forward Embedding in Vertical Federated Learningcited by 27
  4. 2019On the Global Optima of Kernelized Adversarial Representation Learningcited by 14
  5. 2021Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learningcited by 14
  6. 2019Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Recordscited by 11
  7. 2022Impact of Adversarial Training on Robustness and Generalizability of Language Modelscited by 9
  8. 2023East: Efficient and Accurate Secure Transformer Framework for Inferencecited by 9
  9. 2022Privacy-Aware Adversarial Network in Human Mobility Predictioncited by 2
  10. 2024Share Secrets for Privacy: Confidential Forecasting with Vertical Federated Learningcited by 2
  11. 2026LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicingcited by 2

Built on by

Not cited yet.