Cover Image

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Guang, Zhang, Yuhui, Guo, Zimu, Zhao, Lutan, Chen, Xiaojun, Wang, Chen, Wang, Wenhao, Meng, Dan, Hou, Rui
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Chameleon: An Efficient FHE Scheme Switching Acceleration on GPUs
by: Wang, Zhiwei, et al.
Published: (2024)

Accelerating Private Large Transformers Inference through Fine-grained Collaborative Computation
by: Chen, Yuntian, et al.
Published: (2024)

Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference
by: Xu, Xiangrui, et al.
Published: (2024)

FeatureBleed: Inferring Private Enriched Attributes From Sparsity-Optimized AI Accelerators
by: Asher, Darsh, et al.
Published: (2026)

PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN
by: Zheng, Fei, et al.
Published: (2024)

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

ConfusionPrompt: Practical Private Inference for Online Large Language Models
by: Mai, Peihua, et al.
Published: (2023)

The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems
by: Song, Linke, et al.
Published: (2024)

Machine Unlearning in Large Language Models
by: Chen, Kongyang, et al.
Published: (2024)

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

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

ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
by: Xie, Jin, et al.
Published: (2025)

ProphetFuzz: Fully Automated Prediction and Fuzzing of High-Risk Option Combinations with Only Documentation via Large Language Model
by: Wang, Dawei, et al.
Published: (2024)

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

High-Throughput and Scalable Secure Inference Protocols for Deep Learning with Packed Secret Sharing
by: Zhang, Qinghui, et al.
Published: (2026)

Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache
by: Yu, Ye, et al.
Published: (2026)

Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning
by: Wang, Wenhao, et al.
Published: (2026)

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models
by: Meng, Xiangtao, et al.
Published: (2026)

InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
by: Tong, Meng, et al.
Published: (2023)

xMLP: Revolutionizing Private Inference with Exclusive Square Activation
by: Li, Jiajie, et al.
Published: (2024)

The Road to Trust: Building Enclaves within Confidential VMs
by: Wang, Wenhao, et al.
Published: (2024)

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

Membership Inference Attacks on Tokenizers of Large Language Models
by: Tong, Meng, et al.
Published: (2025)

PSA: Private Set Alignment for Secure and Collaborative Analytics on Large-Scale Data
by: Wang, Jiabo, et al.
Published: (2024)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
by: Zhang, Shenyi, et al.
Published: (2025)

Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies
by: Wang, Zhanyu, et al.
Published: (2022)

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

Breaking Euston: Recovering Private Inputs from Secure Inference by Exploiting Subspace Leakage
by: Zhao, Jiaqi, et al.
Published: (2026)

Adaptively Private Next-Token Prediction of Large Language Models
by: Flemings, James, et al.
Published: (2024)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
by: Sha, Haichao, et al.
Published: (2026)

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

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

Benchmarking Differentially Private Tabular Data Synthesis
by: Chen, Kai, et al.
Published: (2025)

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
by: Diaa, Abdulrahman, et al.
Published: (2023)

FederBoost: Private Federated Learning for GBDT
by: Tian, Zhihua, et al.
Published: (2020)

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

Auditing Private Prediction
by: Chadha, Karan, et al.
Published: (2024)

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

A Survey on Private Transformer Inference
by: Li, Yang, et al.
Published: (2024)