Copertina

UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zeng, Wenxuan, Yang, Chao, Xu, Tianshi, Zhang, Bo, Ren, Changrui, Dong, Jin, Li, Meng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EQO: Exploring Ultra-Efficient Private Inference with Winograd-Based Protocol and Quantization Co-Optimization
di: Zeng, Wenxuan, et al.
Pubblicazione: (2024)

PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
di: Xu, Tianshi, et al.
Pubblicazione: (2024)

HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference
di: Xu, Tianshi, et al.
Pubblicazione: (2024)

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
di: Zeng, Wenxuan, et al.
Pubblicazione: (2025)

PrivCirNet: Efficient Private Inference via Block Circulant Transformation
di: Xu, Tianshi, et al.
Pubblicazione: (2024)

Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives
di: Zeng, Wenxuan, et al.
Pubblicazione: (2025)

FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
di: Lin, Chenqi, et al.
Pubblicazione: (2024)

Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC
di: Xu, Tianshi, et al.
Pubblicazione: (2025)

Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt
di: Gu, Yujie, et al.
Pubblicazione: (2026)

CryptPEFT: Efficient and Private Neural Network Inference via Parameter-Efficient Fine-Tuning
di: Xia, Saisai, et al.
Pubblicazione: (2025)

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
di: Zhou, Yifan, et al.
Pubblicazione: (2025)

Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference
di: Garimella, Karthik, et al.
Pubblicazione: (2025)

Efficient and High-Accuracy Private CNN Inference with Helper-Assisted Malicious Security
di: Wang, Kaiwen, et al.
Pubblicazione: (2025)

Computationally Differentially Private Inner Product Protocols Imply Oblivious Transfer
di: Haitner, Iftach, et al.
Pubblicazione: (2025)

Differentially Private Diffusion Models
di: Dockhorn, Tim, et al.
Pubblicazione: (2022)

Hyena: Optimizing Homomorphically Encrypted Convolution for Private CNN Inference
di: Roh, Hyeri, et al.
Pubblicazione: (2023)

Flash: A Hybrid Private Inference Protocol for Deep CNNs with High Accuracy and Low Latency on CPU
di: Roh, Hyeri, et al.
Pubblicazione: (2024)

Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption
di: Lee, Junghyun, et al.
Pubblicazione: (2023)

DeepReShape: Redesigning Neural Networks for Efficient Private Inference
di: Jha, Nandan Kumar, et al.
Pubblicazione: (2023)

CipherFormer: Efficient Transformer Private Inference with Low Round Complexity
di: Wang, Weize, et al.
Pubblicazione: (2024)

Lightweight Protocols for Distributed Private Quantile Estimation
di: Aamand, Anders, et al.
Pubblicazione: (2025)

Multi-Party Private Set Intersection: A Circuit-Based Protocol with Jaccard Similarity for Secure and Efficient Anomaly Detection in Network Traffic
di: Su, Jiuheng, et al.
Pubblicazione: (2024)

Efficient Fuzzy Private Set Intersection from Secret-shared OPRF
di: Yang, Xinpeng, et al.
Pubblicazione: (2026)

PRIVMARK: Private Large Language Models Watermarking with MPC
di: Fargues, Thomas, et al.
Pubblicazione: (2025)

Public-Key Encryption from the MinRank Problem
di: Chatterjee, Rohit, et al.
Pubblicazione: (2025)

Almost-Free Queue Jumping for Prior Inputs in Private Neural Inference
di: Zhang, Qiao, et al.
Pubblicazione: (2026)

Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems
di: Nissim, Kobbi, et al.
Pubblicazione: (2025)

EPSpatial: Achieving Efficient and Private Statistical Analytics of Geospatial Data
di: Zhang, Chuan, et al.
Pubblicazione: (2025)

CipherPrune: Efficient and Scalable Private Transformer Inference
di: Zhang, Yancheng, et al.
Pubblicazione: (2025)

HE-LRM: Efficient Private Embedding Lookups for Neural Inference Using Fully Homomorphic Encryption
di: Garimella, Karthik, et al.
Pubblicazione: (2025)

Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
di: Bao, Wenxuan, et al.
Pubblicazione: (2025)

A Provably Secure Network Protocol for Private Communication with Analysis and Tracing Resistance
di: Ge, Chao, et al.
Pubblicazione: (2025)

Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective
di: Arcolezi, Héber H., et al.
Pubblicazione: (2023)

Automatic State Machine Inference for Binary Protocol Reverse Engineering
di: Yang, Junhai, et al.
Pubblicazione: (2024)

Privacy-Preserving Inference for Quantized BERT Models
di: Lu, Tianpei, et al.
Pubblicazione: (2025)

Secure Transformer Inference Protocol
di: Yuan, Mu, et al.
Pubblicazione: (2023)

Algorithms for Sparse LPN and LSPN Against Low-noise
di: Chen, Xue, et al.
Pubblicazione: (2024)

An Iconic Heavy Hitter Algorithm Made Private
di: Holland, Rayne
Pubblicazione: (2025)

Publicly Verifiable Private Information Retrieval Protocols Based on Function Secret Sharing
di: Zhu, Lin, et al.
Pubblicazione: (2025)

Data Poisoning Attacks to Locally Differentially Private Frequent Itemset Mining Protocols
di: Tong, Wei, et al.
Pubblicazione: (2024)