Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
Not on the map. Why?
Abstract (arXiv)
Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication overhead that is incurred when applied at scale. In this paper, we present an overview of our efforts to bridge the gap between this overhead and practicality for privacy-preserving learning systems using multi-party computation (MPC), zero-knowledge proofs (ZKPs), and fully homomorphic encryption (FHE). Through meticulous hardware/software/algorithm co-design, we show progress towards enabling LLM-scale applications in privacy-preserving settings. We demonstrate the efficacy of our solutions in several contexts, including DNN IP ownership, ethical LLM usage enforcement, and transformer inference.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 29 Sep 2025.
Builds on
33 of 64 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
- 2023Qwen Technical Reportcited by 3,344
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
- 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
- 2014FitNets: Hints for Thin Deep Netscited by 1,653
- 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
- 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
- 2020Efficient Transformers: A Surveycited by 790
- 2023A Comprehensive Overview of Large Language Modelscited by 648
21 more
- 2020MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devicescited by 482
- 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 384
- 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
- 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
- 2023Auditing large language models: a three-layered approachcited by 137
- 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
- 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
- 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 26
- 2025A Survey of Zero-Knowledge Proof Based Verifiable Machine Learningcited by 22
- 2024BotSim: LLM-Powered Malicious Social Botnet Simulationcited by 21
- 2021Privacy enabled Financial Text Classification using Differential Privacy and Federated Learningcited by 18
- 2024EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Modelscited by 11
- 2023LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medical Specialtiescited by 10
- 2023ZKROWNN: Zero Knowledge Right of Ownership for Neural Networkscited by 6
- 2024Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactionscited by 6
- 2022Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardwarecited by 2
- 2024SZKP: A Scalable Accelerator Architecture for Zero-Knowledge Proofscited by 2
- 2021Privacy-Preserving Biometric Matching Using Homomorphic Encryptioncited by 1
- 2024if-ZKP: Intel FPGA-Based Acceleration of Zero Knowledge Proofscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.