Image de couverture de livre

The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Choi, Chanwoo, Kim, Jinsoo, Cho, Sukmin, Jeong, Soyeong, Chang, Buru
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks
par: Bagwe, Gaurav, et autres
Publié: (2025)

ProveRAG: Provenance-Driven Vulnerability Analysis with Automated Retrieval-Augmented LLMs
par: Fayyazi, Reza, et autres
Publié: (2024)

PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
par: Wang, Baiqiang, et autres
Publié: (2025)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
par: Zhang, Yucheng, et autres
Publié: (2024)

Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models
par: Gong, Yuyang, et autres
Publié: (2025)

Traceback of Poisoning Attacks to Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

Practical Poisoning Attacks against Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

Secure Retrieval-Augmented Generation against Poisoning Attacks
par: Cheng, Zirui, et autres
Publié: (2025)

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
par: Xue, Jiaqi, et autres
Publié: (2024)

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
par: Liang, Xun, et autres
Publié: (2025)

Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
par: Liu, Mingrui, et autres
Publié: (2024)

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
par: Yin, Yu, et autres
Publié: (2026)

Retrieval-Augmented Review Generation for Poisoning Recommender Systems
par: Yang, Shiyi, et autres
Publié: (2025)

Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks
par: Wang, Zongwei, et autres
Publié: (2023)

BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation
par: Gao, Chengcai, et autres
Publié: (2026)

Words Blending Boxes. Obfuscating Queries in Information Retrieval using Differential Privacy
par: De Faveri, Francesco Luigi, et autres
Publié: (2024)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
par: Yao, Mengyu, et autres
Publié: (2026)

Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
par: Liu, Yu, et autres
Publié: (2026)

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
par: Gong, Yuyang, et autres
Publié: (2026)

Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion
par: Thornton, Scott
Publié: (2026)

A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain
par: Lu, Yining, et autres
Publié: (2025)

Sift or Get Off the PoC: Applying Information Retrieval to Vulnerability Research with SiftRank
par: Gross, Caleb
Publié: (2025)

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
par: Mishra, Saroj, et autres
Publié: (2026)

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
par: Cheng, Yihang, et autres
Publié: (2024)

Exposing Privacy Risks in Graph Retrieval-Augmented Generation
par: Liu, Jiale, et autres
Publié: (2025)

Differentially Private Datastore Generation for Retrieval-Augmented Inference
par: Abouelenein, Abdelrahman, et autres
Publié: (2026)

Poisoning Attacks and Defenses in Recommender Systems: A Survey
par: Wang, Zongwei, et autres
Publié: (2024)

MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation
par: Simoni, Marco, et autres
Publié: (2024)

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

KnowML: Improving Generalization of ML-NIDS with Attack Knowledge Graphs
par: Guo, Xin Fan, et autres
Publié: (2025)

Exposing Citation Vulnerabilities in Generative Engines
par: Mochizuki, Riku, et autres
Publié: (2025)

Versatile and Fast Location-Based Private Information Retrieval with Fully Homomorphic Encryption over the Torus
par: Yoo, Joon Soo, et autres
Publié: (2025)

Impedance vs. Power Side-channel Vulnerabilities: A Comparative Study
par: Awal, Md Sadik, et autres
Publié: (2024)

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
par: Yang, Hongjang, et autres
Publié: (2026)

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
par: Lv, Peizhuo, et autres
Publié: (2025)

Upcycling Candidate Tokens of Large Language Models for Query Expansion
par: Kim, Jinseok, et autres
Publié: (2025)

Adversarial Hubness in Multi-Modal Retrieval
par: Zhang, Tingwei, et autres
Publié: (2024)

Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
par: Liu, Yu-An, et autres
Publié: (2024)

An Effective Energy Mask-based Adversarial Evasion Attacks against Misclassification in Speaker Recognition Systems
par: Park, Chanwoo, et autres
Publié: (2026)