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

arXiv:2605.28112 · cs.CR, cs.CL, cs.IR · Submitted 2026-05-27 · Read on arXiv

cs.CR, cs.CL, cs.IR

Submitted: 2026-05-27

Updated: 2026-08-28

Code: https://github.com/Junjie-Mu/routing-hijacking-fedrag

Terminology

• Hallucination — 16× in this paper · explained in 3 episodes
• RAG — 15× in this paper · explained in 3 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation — 11× in this paper
• Ablation — 10× in this paper · explained in 1 episode
• Robustness — 8× in this paper · explained in 5 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Sycophancy — 7× in this paper · explained in 4 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Trust-Aware Secure Routing — 4× in this paper
• Federated Learning — 3× in this paper · explained in 15 episodes
• Federated Learning (FL) — 3× in this paper · explained in 7 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Byzantine-robust Federated Learning — 1× in this paper
• Clustering — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Geographic Information Systems — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System
• Federated Retrieval-Augmented Generation: A Systematic Mapping Study
• UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
• The Llama 3 Herd of Models
• What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
• Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare
• C-Pack: Packed Resources For General Chinese Embeddings
• CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
• Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation
• Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
• Qwen3 Technical Report
• A Deep Dive into Fairness, Bias, Threats, and Privacy in Recommender Systems: Insights and Future Research
• MedGemma Technical Report
• FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs