← Back to all news
arXiv AI By Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang

LaCache: Robust Semantic Caching for LLM Serving

Read the original on arXiv AI →

LaCache introduces a redesigned semantic caching mechanism for large language model (LLM) serving that defends against cache‑collision attacks. By shifting integrity checks from queries to the first $k$ speculatively decoded tokens of the LLM response, LaCache can detect adversarial cache pollution with provable high probability. Experiments across multiple LLMs and benchmarks show that LaCache reduces attack hit rates to near zero while retaining over 90% of benign cache utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 3

Inference Cost Attacks for Retrieval-Augmented Large Language Models

arXiv:2606. 02643v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources.

By Chengliang Liu, Liangbo Ning, Yujuan Ding, Wenqi Fan
llmsragagentsreinforcement-learningroboticssafety
More like this →
arXiv Computation and Language
Aug 31

A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG

The paper exposes a new vulnerability in Federated Retrieval-Augmented Generation (FedRAG) called Routing Hijacking, where a malicious client forges its semantic profile to attract target queries despite lacking relevant data. Experiments across three FedRAG routing architectures show that this attack consistently misroutes queries, causing downstream failures such as missing evidence, poisoning, incorrect answers, hallucinations, and sycophantic behavior. The authors propose a trust‑aware post‑routing framework that reweights clients based on evidence feedback, which effectively suppresses persistent hijacking and transfers to a learned neural router.

By Junjie Mu, Qiongxiu Li
ragroboticssafety
More like this →
arXiv Computation and Language
Aug 31

CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents

arXiv:2608. 28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers.

By Jaewon Jung, Haizhong Zheng, Hongsun Jang, Jaeyong Song, Beidi Chen, Jinho Lee
llmsragmultimodalbenchmarkssafety
More like this →