Cover Image

One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shereen, Ezzeldin, Ristea, Dan, McFadden, Shae, Hasircioglu, Burak, Mavroudis, Vasilios, Hicks, Chris
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Computer Vision and Pattern Recognition Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points
by: Ristea, Dan, et al.
Published: (2024)

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
by: Souly, Alexandra, et al.
Published: (2025)

A Mechanism for Optimizing Media Recommender Systems
by: McFadden, Brian
Published: (2024)

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation
by: Ristea, Dan, et al.
Published: (2024)

Referential Security as a New Paradigm for AI Evaluations
by: Ristea, Dan, et al.
Published: (2026)

DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
by: McFadden, Shae, et al.
Published: (2025)

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

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
by: McFadden, Shae, et al.
Published: (2026)

Recall Them All: Retrieval-Augmented Language Models for Long Object List Extraction from Long Documents
by: Singhania, Sneha, et al.
Published: (2024)

Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation
by: Salemi, Alireza, et al.
Published: (2025)

VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
by: Tanaka, Ryota, et al.
Published: (2025)

From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs
by: Abuadbba, Alsharif, et al.
Published: (2025)

Environment Complexity and Nash Equilibria in a Sequential Social Dilemma
by: Yasir, Mustafa, et al.
Published: (2024)

Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
by: Samarinas, Chris, et al.
Published: (2026)

Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval
by: Li, Yongkang, et al.
Published: (2025)

Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval
by: Li, Yongkang, et al.
Published: (2025)

Attention Grounded Enhancement for Visual Document Retrieval
by: Cui, Wanqing, et al.
Published: (2025)

TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
by: Yu, Xiaohan, et al.
Published: (2025)

Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
by: Shen, Wenxuan, et al.
Published: (2025)

Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
by: Dong, Kuicai, et al.
Published: (2025)

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
by: Yan, Yibo, et al.
Published: (2026)

Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey
by: Zhang, Xiantao
Published: (2025)

AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
by: Song, Hongru, et al.
Published: (2026)

Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
by: Liu, Xunzhuo, et al.
Published: (2026)

Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images
by: Xiao, Bin, et al.
Published: (2023)

RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish
by: Köse, Süha Kağan, et al.
Published: (2026)

Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
by: Kim, Juyeon, et al.
Published: (2025)

Evaluating Retrieval Quality in Retrieval-Augmented Generation
by: Salemi, Alireza, et al.
Published: (2024)

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
by: Wang, Qiuchen, et al.
Published: (2025)

Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation
by: Stankovic, Mile
Published: (2025)

Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method
by: Chen, Peter Baile, et al.
Published: (2025)

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
by: Yan, Yibo, et al.
Published: (2026)

Chain-of-Retrieval Augmented Generation
by: Wang, Liang, et al.
Published: (2025)

Parametric Retrieval Augmented Generation
by: Su, Weihang, et al.
Published: (2025)

Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
by: Yan, Yibo, et al.
Published: (2026)

CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval
by: Chi, Yizhou, et al.
Published: (2024)

A Large Language Model-based Framework for Semi-Structured Tender Document Retrieval-Augmented Generation
by: Zhao, Yilong, et al.
Published: (2024)

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
by: Long, Xinwei, et al.
Published: (2025)

VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents
by: Huwiler, Daniel, et al.
Published: (2025)

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation
by: Ni, Jingwei, et al.
Published: (2024)