mlsanityData to 7 Oct 2026

Primer: Fast Private Transformer Inference on Encrypted Data

arXiv 2303.13679 ↗First posted 23 Mar 2023cs.CRcited by 19

Not on the map. Why?

Abstract (arXiv)

It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular methods to support private Transformer inference. However, existing works still suffer from prohibitively computational and communicational overhead. In this work, we present, Primer, to enable a fast and accurate Transformer over encrypted data for natural language processing tasks. In particular, Primer is constructed by a hybrid cryptographic protocol optimized for attention-based Transformer models, as well as techniques including computation merge and tokens-first ciphertext packing. Comprehensive experiments on encrypted language modeling show that Primer achieves state-of-the-art accuracy and reduces the inference latency by 90.6% ~ 97.5% over previous methods.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 7; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 48
  2. 2024PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restorationcited by 27
  3. 2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
  4. 2023Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryptioncited by 19
  5. 2024No Free Lunch Theorem for Privacy-Preserving LLM Inferencecited by 13
  6. 2023East: Efficient and Accurate Secure Transformer Framework for Inferencecited by 9
  7. 2025CipherPrune: Efficient and Scalable Private Transformer Inferencecited by 9
  8. 2024SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPCcited by 7
  9. 2024Power-Softmax: Towards Secure LLM Inference over Encrypted Datacited by 6
  10. 2024CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inferencecited by 6
  11. 2025Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfercited by 5
  12. 2025TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generationcited by 4
7 more
  1. 2024CryptoTrain: Fast Secure Training on Encrypted Datasetcited by 3
  2. 2025Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Acceleratorscited by 2
  3. 2024TruncFormer: Private LLM Inference Using Only Truncationscited by 1
  4. 2025Private Transformer Inference in MLaaS: A Surveycited by 1
  5. 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradientscited by 1
  6. 2025Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representationscited by 1
  7. 2026RobPI: Robust Private Inference against Malicious Clientcited by 0