Cover Image

Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Thornton, Scott
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Information Retrieval Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Traceback of Poisoning Attacks to Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

Practical Poisoning Attacks against Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

Secure Retrieval-Augmented Generation against Poisoning Attacks
by: Cheng, Zirui, et al.
Published: (2025)

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

HGAttack: Transferable Heterogeneous Graph Adversarial Attack
by: Zhao, He, et al.
Published: (2024)

DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks
by: Chen, Jinyin, et al.
Published: (2024)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
by: Yao, Mengyu, et al.
Published: (2026)

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

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

Adversarial Attacks to Multi-Modal Models
by: Dou, Zhihao, et al.
Published: (2024)

Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks
by: Wang, Zongwei, et al.
Published: (2023)

Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures
by: Nguyen, Thanh Toan, et al.
Published: (2024)

Differentially Private Datastore Generation for Retrieval-Augmented Inference
by: Abouelenein, Abdelrahman, et al.
Published: (2026)

Few-shot Model Extraction Attacks against Sequential Recommender Systems
by: Zhang, Hui, et al.
Published: (2024)

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

Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
by: Liu, Yu-An, et al.
Published: (2024)

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
by: Zhang, Baolei, et al.
Published: (2025)

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

AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Security
by: Freitas, Scott, et al.
Published: (2024)

Differentially Private Graph Diffusion with Applications in Personalized PageRanks
by: Wei, Rongzhe, et al.
Published: (2024)

Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach
by: Hu, Wentao, et al.
Published: (2023)

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

Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
by: Thornton, Scott
Published: (2026)

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

Mining Temporal Attack Patterns from Cyberthreat Intelligence Reports
by: Rahman, Md Rayhanur, et al.
Published: (2024)

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

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

Safe machine learning model release from Trusted Research Environments: The SACRO-ML package
by: Smith, Jim, et al.
Published: (2022)

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

Randomized algorithms for precise measurement of differentially-private, personalized recommendations
by: Laro, Allegra, et al.
Published: (2023)

A Privacy Preserving System for Movie Recommendations Using Federated Learning
by: Neumann, David, et al.
Published: (2023)

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
by: Lim, Juntaek, et al.
Published: (2024)

How to Forget Clients in Federated Online Learning to Rank?
by: Wang, Shuyi, et al.
Published: (2024)

Poisoning Federated Recommender Systems with Fake Users
by: Yin, Ming, et al.
Published: (2024)

Effective and secure federated online learning to rank
by: Wang, Shuyi
Published: (2024)

Watermarking Recommender Systems
by: Zhang, Sixiao, et al.
Published: (2024)

Preserving Privacy and Utility in LLM-Based Product Recommendations
by: Khezresmaeilzadeh, Tina, et al.
Published: (2025)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
by: Chen, Zhaorun, et al.
Published: (2024)

Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios
by: Rong, Dazhong, et al.
Published: (2022)

POST: Email Archival, Processing and Flagging Stack for Incident Responders
by: Fairbanks, Jeffrey
Published: (2024)