Copertina

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Guanlong, li, Zhaohan, Zhang, Yao, Zhang, Zheng, Niu, Jianyu, Wu, Ye, Zhang, Yinqian
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing
di: Wang, Rui, et al.
Pubblicazione: (2025)

NetEcho: From Real-World Streaming Side-Channels to Full LLM Conversation Recovery
di: Zhang, Zheng, et al.
Pubblicazione: (2025)

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
di: Chu, Kexin, et al.
Pubblicazione: (2025)

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

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
di: Luo, Zhifan, et al.
Pubblicazione: (2025)

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

CryptoGen: Secure Transformer Generation with Encrypted KV-Cache Reuse
di: Zhang, Hedong, et al.
Pubblicazione: (2026)

TeeRollup: Efficient Rollup Design Using Heterogeneous TEE
di: Wen, Xiaoqing, et al.
Pubblicazione: (2024)

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems
di: Yamamoto, Yuji, et al.
Pubblicazione: (2026)

Demystifying Private Transactions and Their Impact in PoW and PoS Ethereum
di: Lyu, Xingyu, et al.
Pubblicazione: (2025)

RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
di: Liu, Mingrui, et al.
Pubblicazione: (2026)

BackCache: Mitigating Contention-Based Cache Timing Attacks by Hiding Cache Line Evictions
di: Wang, Quancheng, et al.
Pubblicazione: (2023)

Whose Narrative is it Anyway? A KV Cache Manipulation Attack
di: Ganesh, Mukkesh, et al.
Pubblicazione: (2025)

MAGE: Mutual Attestation for a Group of Enclaves without Trusted Third Parties
di: Chen, Guoxing, et al.
Pubblicazione: (2020)

MECURY: Practical Cross-Chain Exchange via Trusted Hardware
di: Wen, Xiaoqing, et al.
Pubblicazione: (2024)

Leader Rotation Is Not Enough: Scrutinizing Leadership Democracy of Chained BFT Consensus
di: Tang, Yining, et al.
Pubblicazione: (2025)

Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation
di: Chen, Yufei, et al.
Pubblicazione: (2025)

Addendum: Systematic Evaluation of Randomized Cache Designs against Cache Occupancy
di: Chakraborty, Anirban, et al.
Pubblicazione: (2025)

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
di: Bai, Li, et al.
Pubblicazione: (2025)

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

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
di: Yang, Huan, et al.
Pubblicazione: (2024)

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
di: Zhang, Zhixiang, et al.
Pubblicazione: (2026)

Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)
di: Lin, Yu, et al.
Pubblicazione: (2026)

Smart Privacy Policy Assistant: An LLM-Powered System for Transparent and Actionable Privacy Notices
di: Kalvakuntla, Sriharshini, et al.
Pubblicazione: (2026)

Unraveling Responsiveness of Chained BFT Consensus with Network Delay
di: Tang, Yining, et al.
Pubblicazione: (2025)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
di: Wang, Longxiang, et al.
Pubblicazione: (2026)

Hidden Web Caches Discovery
di: Golinelli, Matteo, et al.
Pubblicazione: (2024)

A Near-Cache Architectural Framework for Cryptographic Computing
di: Zhang, Jingyao, et al.
Pubblicazione: (2025)

The Avatar Cache: Enabling On-Demand Security with Morphable Cache Architecture
di: Bhatla, Anubhav, et al.
Pubblicazione: (2026)

Random and Safe Cache Architecture to Defeat Cache Timing Attacks
di: Hu, Guangyuan, et al.
Pubblicazione: (2023)

Systematic Evaluation of Randomized Cache Designs against Cache Occupancy
di: Chakraborty, Anirban, et al.
Pubblicazione: (2023)

CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs
di: Fahey, Ryan
Pubblicazione: (2026)

Write+Sync: Software Cache Write Covert Channels Exploiting Memory-disk Synchronization
di: Chen, Congcong, et al.
Pubblicazione: (2023)

A Survey on Privacy-Preserving Caching at Network Edge: Classification, Solutions, and Challenges
di: Zhang, Xianzhi, et al.
Pubblicazione: (2024)

Efficient RL-based Cache Vulnerability Exploration by Penalizing Useless Agent Actions
di: Nakanishi, Kanato, et al.
Pubblicazione: (2025)

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems
di: Pennas, Panagiotis Georgios, et al.
Pubblicazione: (2026)

Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
di: Zhang, Yixiang, et al.
Pubblicazione: (2025)

FACOS: Enabling Privacy Protection Through Fine-Grained Access Control with On-chain and Off-chain System
di: Liu, Chao, et al.
Pubblicazione: (2024)

RollingCache: Using Runtime Behavior to Defend Against Cache Side Channel Attacks
di: Ojha, Divya, et al.
Pubblicazione: (2024)

Attacks on Approximate Caches in Text-to-Image Diffusion Models
di: Sun, Desen, et al.
Pubblicazione: (2025)