← Back to all news
arXiv Computation and Language By Junjie Mu, Qiongxiu Li

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

Read the original on arXiv Computation and Language →

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.

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 Computation and Language.

Related stories

arXiv Machine Learning
4d ago

Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

The paper investigates a new security vulnerability in fine‑tuned Mixture‑of‑Experts large language models, termed structural memorization, where the model not only memorizes training data but also the internal routing pathways used during fine‑tuning. The authors demonstrate that these memorized expert pathways can be recovered from the model’s unconditional generation using only routing and output logits, even without access to the fine‑tuning data. They further show that this vulnerability is amplified in distributed deployments and that traditional membership inference metrics fail to detect it, proposing composite metrics that improve detection of memorized routing structures.

By Fei Wang, Baochun Li, Bo Li
llmsroboticsfine-tuning
More like this →
arXiv AI
6d ago

Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories

The paper investigates how large language model (LLM) search agents can be manipulated through repeated, coordinated search-result injections, a threat that extends beyond single-page poisoning. It introduces Authority‑Chain Hijack (ACH), a strategy that chains manipulated evidence across multiple sources, achieving high attack success rates on the SafeSearch benchmark. The authors also present Trace‑Guided Strategy Evolution (TGSE), an automated method that refines attacker strategies using execution traces, further improving success rates.

By Xuebin Li, Hanqing Zhao, Siyuan Liang, Kejiang Chen, Weiming Zhang, Dacheng Tao, Nenghai Yu
llmsagentsmultimodalsafety
More like this →
arXiv Machine Learning
Oct 2

Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

The paper proposes using lossy compression as a security signal in federated learning by defining a "compression footprint"—a low‑dimensional set of statistics derived from the compressor’s output. It introduces CRAFT, a server‑side aggregation method that leverages these footprints to distinguish honest from malicious updates without extra client metadata or knowledge of attacker numbers. Experiments on six attacks and datasets show CRAFT often outperforms existing robust aggregation baselines, demonstrating that compression can simultaneously reduce communication and enhance security.

By Sachi Shome, William Eiers
efficiency
More like this →