Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mu, Junjie, Li, Qiongxiu
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Computation and Language Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
por: Dilworth, Robert
Publicado: (2026)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
por: Zhang, Yucheng, et al.
Publicado: (2024)

Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models
por: Gong, Yuyang, et al.
Publicado: (2025)

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
por: Cheng, Yihang, et al.
Publicado: (2024)

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
por: Mishra, Saroj, et al.
Publicado: (2026)

Retrieval-Augmented Review Generation for Poisoning Recommender Systems
por: Yang, Shiyi, et al.
Publicado: (2025)

A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain
por: Lu, Yining, et al.
Publicado: (2025)

StegoStylo: Squelching Stylometric Scrutiny through Steganographic Stitching
por: Dilworth, Robert
Publicado: (2026)

Exposing Citation Vulnerabilities in Generative Engines
por: Mochizuki, Riku, et al.
Publicado: (2025)

Tuning for TraceTarnish: Techniques, Trends, and Testing Tangible Traits
por: Dilworth, Robert
Publicado: (2025)

Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution
por: Dilworth, Robert
Publicado: (2025)

Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
por: Carranza, Aldo Gael, et al.
Publicado: (2023)

DV-FSR: A Dual-View Target Attack Framework for Federated Sequential Recommendation
por: Qin, Qitao, et al.
Publicado: (2024)

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
por: Cooper, Portia, et al.
Publicado: (2024)

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
por: Xue, Jiaqi, et al.
Publicado: (2024)

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
por: Shah, Syed Huma
Publicado: (2026)

The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems
por: Choi, Chanwoo, et al.
Publicado: (2025)

Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
por: Liu, Yu, et al.
Publicado: (2026)

A Robust Cybersecurity Topic Classification Tool
por: Pelofske, Elijah, et al.
Publicado: (2021)

ProveRAG: Provenance-Driven Vulnerability Analysis with Automated Retrieval-Augmented LLMs
por: Fayyazi, Reza, et al.
Publicado: (2024)

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
por: Yang, Shiyi, et al.
Publicado: (2025)

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
por: Yin, Yu, et al.
Publicado: (2026)

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks
por: Bagwe, Gaurav, et al.
Publicado: (2025)

Beyond Similarity: Personalized Federated Recommendation with Composite Aggregation
por: Zhang, Honglei, et al.
Publicado: (2024)

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
por: Gong, Yuyang, et al.
Publicado: (2026)

Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations
por: Salemi, Alireza, et al.
Publicado: (2026)

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
por: Deguchi, Hiroyuki, et al.
Publicado: (2026)

Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
por: Zhao, Shuai, et al.
Publicado: (2024)

Token-wise Influential Training Data Retrieval for Large Language Models
por: Lin, Huawei, et al.
Publicado: (2024)

PII-Bench: Evaluating Query-Aware Privacy Protection Systems
por: Shen, Hao, et al.
Publicado: (2025)

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
por: Simoni, Marco, et al.
Publicado: (2025)

Secure Federated Graph-Filtering for Recommender Systems
por: Nicolas, Julien, et al.
Publicado: (2025)

Non-Random Data Encodes its Geometric and Topological Dimensions
por: Zenil, Hector, et al.
Publicado: (2024)

Securing RAG: A Risk Assessment and Mitigation Framework
por: Ammann, Lukas, et al.
Publicado: (2025)

PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
por: Wang, Baiqiang, et al.
Publicado: (2025)

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
por: Liang, Xun, et al.
Publicado: (2025)

One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
por: Shereen, Ezzeldin, et al.
Publicado: (2025)

Auditing Privacy in Multi-Tenant RAG under Account Collusion
por: Burnat, Florian A. D.
Publicado: (2026)

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
por: Guo, Junfeng, et al.
Publicado: (2025)

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
por: Liu, Kangwei, et al.
Publicado: (2025)