Imagen de Portada

Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Yu, Zhang, Qizhi, Ruan, Wenqiang, Zhang, Daode, Hong, Jue, Wu, Ye, Xia, Hanning, Mao, Yunlong, Zhong, Sheng
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

OFL: Opportunistic Federated Learning for Resource-Heterogeneous and Privacy-Aware Devices
por: Mao, Yunlong, et al.
Publicado: (2025)

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

SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
por: Zhu, Chengcheng, et al.
Publicado: (2025)

LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation
por: He, Ying, et al.
Publicado: (2024)

Privacy-Enhanced Database Synthesis for Benchmark Publishing (Technical Report)
por: Ge, Yunqing, et al.
Publicado: (2024)

No Free Lunch Theorem for Privacy-Preserving LLM Inference
por: Zhang, Xiaojin, et al.
Publicado: (2024)

Disassembling Obfuscated Executables with LLM
por: Rong, Huanyao, et al.
Publicado: (2024)

A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
por: Li, Xiao, et al.
Publicado: (2025)

Towards Privacy-Preserving Split Learning: Destabilizing Adversarial Inference and Reconstruction Attacks in the Cloud
por: Higgins, Griffin, et al.
Publicado: (2025)

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
por: Wang, Shouju, et al.
Publicado: (2025)

On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
por: Wang, Zijian, et al.
Publicado: (2025)

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

FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation
por: Gu, Hanlin, et al.
Publicado: (2024)

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
por: Wu, Guanlong, et al.
Publicado: (2026)

Privacy-Preserving Quantum Annealing for Quadratic Unconstrained Binary Optimization (QUBO) Problems
por: Xie, Moyang, et al.
Publicado: (2024)

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

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
por: Zhang, Kaiyuan, et al.
Publicado: (2025)

Knowledge-Assisted Privacy Preserving in Semantic Communication
por: Liu, Xuesong, et al.
Publicado: (2024)

Towards LLM-Based Analysis of Virtualization-Obfuscated Code through Automated Data Generation
por: An, Sangjun, et al.
Publicado: (2026)

Confidential Prompting: Privacy-preserving LLM Inference on Cloud
por: Li, Caihua, et al.
Publicado: (2024)

SecureNT: Smart Topology Obfuscation for Privacy-Aware Network Monitoring
por: Du, Chengze, et al.
Publicado: (2024)

Understanding and Characterizing Obfuscated Funds Transfers in Ethereum Smart Contracts
por: Sheng, Zhang, et al.
Publicado: (2025)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
por: Noorbakhsh, Sayedeh Leila, et al.
Publicado: (2024)

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
por: Li, Zi, et al.
Publicado: (2026)

Privacy-Preserving Credit Card Approval Using Homomorphic SVM: Toward Secure Inference in FinTech Applications
por: Faneela, et al.
Publicado: (2025)

Advancing Obfuscation Strategies to Counter China's Great Firewall: A Technical and Policy Perspective
por: Li, Li
Publicado: (2025)

OnePath: Efficient and Privacy-Preserving Decision Tree Inference in the Cloud
por: Yuan, Shuai, et al.
Publicado: (2024)

Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
por: Yu, Honglan, et al.
Publicado: (2025)

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
por: Luo, Jinglong, et al.
Publicado: (2024)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
por: Fu, Jie, et al.
Publicado: (2026)

Technical Report: The Need for a (Research) Sandstorm through the Privacy Sandbox
por: Beugin, Yohan, et al.
Publicado: (2025)

Towards Privacy-Preserving Revocation of Verifiable Credentials with Time-Flexibility
por: Buccafurri, Francesco, et al.
Publicado: (2025)

Privacy-Preserving Hierarchical Model-Distributed Inference
por: Dehkordi, Fatemeh Jafarian, et al.
Publicado: (2024)

Privacy-Preserving Screening for Record Linkage
por: Huang, Chenyu, et al.
Publicado: (2026)

PrivacyGo: Privacy-Preserving Ad Measurement with Multidimensional Intersection
por: Du, Jian, et al.
Publicado: (2025)

Good-Enough LLM Obfuscation (GELO)
por: Belikov, Anatoly, et al.
Publicado: (2026)

Towards Privacy-Preserving Federated Learning using Hybrid Homomorphic Encryption
por: Costa, Ivan, et al.
Publicado: (2026)

Towards Privacy-Preserving Anomaly-Based Intrusion Detection in Energy Communities
por: Afzal, Zeeshan, et al.
Publicado: (2025)

Learning-based Privacy-Preserving Graph Publishing Against Sensitive Link Inference Attacks
por: Wu, Yucheng, et al.
Publicado: (2025)

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
por: Yoon, Jeongho, et al.
Publicado: (2026)