Cover Image

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Rui, Wu, Junda, Xia, Yu, Yu, Tong, Zhang, Ruiyi, Rossi, Ryan, Mitra, Subrata, Yao, Lina, McAuley, Julian
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

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

Pluralistic Off-policy Evaluation and Alignment
by: Huang, Chengkai, et al.
Published: (2025)

DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer
by: Wang, Ruoyu, et al.
Published: (2025)

CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs
by: Fahey, Ryan
Published: (2026)

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

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

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

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

SAND: Boosting LLM Agents with Self-Taught Action Deliberation
by: Xia, Yu, et al.
Published: (2025)

Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation
by: Wang, Ruoyu, et al.
Published: (2025)

Visual Prompting in Multimodal Large Language Models: A Survey
by: Wu, Junda, et al.
Published: (2024)

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

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

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

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

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

Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
by: Xia, Yu, et al.
Published: (2024)

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction
by: Huang, Hongtao, et al.
Published: (2025)

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
by: Huang, Chengkai, et al.
Published: (2025)

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

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

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

Towards Threshold-Free KV Cache Pruning
by: Ni, Xuanfan, et al.
Published: (2025)

Hidden Web Caches Discovery
by: Golinelli, Matteo, et al.
Published: (2024)

Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations
by: Xia, Yu, et al.
Published: (2025)

CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
by: Nahian, Mohaiminul Al, et al.
Published: (2025)

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

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
by: Bui, Ngoc, et al.
Published: (2025)

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

Active Learning for Direct Preference Optimization
by: Kveton, Branislav, et al.
Published: (2025)

PCG: Mitigating Conflict-based Cache Side-channel Attacks with Prefetching
by: Jiang, Fang, et al.
Published: (2024)

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

Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
by: Huang, Chengkai, et al.
Published: (2024)

Federated Large Language Models: Current Progress and Future Directions
by: Yao, Yuhang, et al.
Published: (2024)

EXAM: Exploiting Exclusive System-Level Cache in Apple M-Series SoCs for Enhanced Cache Occupancy Attacks
by: Xu, Tianhong, et al.
Published: (2025)

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
by: Agarwal, Shubham, et al.
Published: (2025)

CacheSquash: Making caches speculation-aware
by: ElAtali, Hossam, et al.
Published: (2024)

Prime+Retouch: When Cache is Locked and Leaked
by: Lee, Jaehyuk, et al.
Published: (2024)

Systematic Assessment of Cache Timing Vulnerabilities on RISC-V Processors
by: Austa, Cédrick, et al.
Published: (2025)

dKV-Cache: The Cache for Diffusion Language Models
by: Ma, Xinyin, et al.
Published: (2025)