Copertina

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yin, Yu, Wang, Shuai, Koopman, Bevan, Zuccon, Guido
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Vulnerability of LLM Rankers to Prompt Injection Attacks
di: Yin, Yu, et al.
Pubblicazione: (2026)

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

AutoBool: An Reinforcement-Learning trained LLM for Effective Automated Boolean Query Generation for Systematic Reviews
di: Wang, Shuai, et al.
Pubblicazione: (2025)

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

Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
di: Zhou, Yongjie, et al.
Pubblicazione: (2026)

Reassessing Large Language Model Boolean Query Generation for Systematic Reviews
di: Wang, Shuai, et al.
Pubblicazione: (2025)

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

Team IELAB at TREC Clinical Trial Track 2023: Enhancing Clinical Trial Retrieval with Neural Rankers and Large Language Models
di: Zhuang, Shengyao, et al.
Pubblicazione: (2024)

Does Vec2Text Pose a New Corpus Poisoning Threat?
di: Zhuang, Shengyao, et al.
Pubblicazione: (2024)

A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR
di: Mao, Xinyu, et al.
Pubblicazione: (2024)

PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
di: Zhuang, Shengyao, et al.
Pubblicazione: (2024)

ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search
di: Wang, Shuai, et al.
Pubblicazione: (2024)

2D Matryoshka Training for Information Retrieval
di: Wang, Shuai, et al.
Pubblicazione: (2024)

Poisoning Attacks and Defenses in Recommender Systems: A Survey
di: Wang, Zongwei, et al.
Pubblicazione: (2024)

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

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

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

Starbucks-v2: Improved Training for 2D Matryoshka Embeddings
di: Zhuang, Shengyao, et al.
Pubblicazione: (2024)

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

KnowML: Improving Generalization of ML-NIDS with Attack Knowledge Graphs
di: Guo, Xin Fan, et al.
Pubblicazione: (2025)

Dense Retrieval with Continuous Explicit Feedback for Systematic Review Screening Prioritisation
di: Mao, Xinyu, et al.
Pubblicazione: (2024)

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

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

Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models
di: Li, Hang, et al.
Pubblicazione: (2025)

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
di: Zhuang, Shengyao, et al.
Pubblicazione: (2025)

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

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

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

RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
di: Liu, Jiawei, et al.
Pubblicazione: (2025)

Whole-Pool Setwise Reranking with Long-Context Language Models
di: Li, Hang, et al.
Pubblicazione: (2026)

TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval
di: Li, Hang, et al.
Pubblicazione: (2024)

On the impact of retrieved content representations in RAG Pipelines
di: Ross, Jonathan J, et al.
Pubblicazione: (2026)

Zero-shot Generative Large Language Models for Systematic Review Screening Automation
di: Wang, Shuai, et al.
Pubblicazione: (2024)

LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
di: Li, Hang, et al.
Pubblicazione: (2025)

Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems
di: Zhuang, Shengyao, et al.
Pubblicazione: (2024)

A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
di: Zhuang, Shengyao, et al.
Pubblicazione: (2023)

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

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

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

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