Image de couverture de livre

RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations

Fuente: Zenodo

Enregistré dans:

Détails bibliographiques
Auteur principal:	ANONYMOUS, ARTIFACTS
Format:	Recurso digital
Publié:	Zenodo 2026
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection
par: Graves, Marcus
Publié: (2026)

Clean Code, Better Models: Enhancing LLM Performance with Smell-Cleaned Dataset
par: ANONYMOUS
Publié: (2025)

Supplementary Documents for "Specifying and Verifying Future Conditions"
par: ANONYMOUS, ANONYMOUS
Publié: (2025)

Supplementary Documents for "Specifying and Verifying Future Conditions"
par: ANONYMOUS, ANONYMOUS
Publié: (2025)

The Unicode cookbook for linguists
par: Moran, Steven, et autres
Publié: (2018)

Contractual Reinforcement Learning: Pulling Arms with Invisible Hands
par: Wu, Jibang, et autres
Publié: (2024)

UAST: Unicode Aware Sanskrit Transliteration
par: Dave, Dhruvil, et autres
Publié: (2022)

Unicode Normalization and Grapheme Parsing of Indic Languages
par: Ansary, Nazmuddoha, et autres
Publié: (2023)

Transcoding Unicode Characters with AVX-512 Instructions
par: Clausecker, Robert, et autres
Publié: (2022)

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

Options for Presentation of Multilingual Text: Use of the Unicode Standard.
par: Erickson, Janet C., et autres
Publié: (1997)

CodeRAG-Bench: Can Retrieval Augment Code Generation?
par: Wang, Zora Zhiruo, et autres
Publié: (2024)

H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations
par: Elchafei, Passant, et autres
Publié: (2026)

LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation
par: Li, Haitao, et autres
Publié: (2025)

DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection
par: Wang, Jerry, et autres
Publié: (2025)

RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance
par: Jiang, Hengjun, et autres
Publié: (2026)

RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
par: Brehme, Lorenz, et autres
Publié: (2026)

Microwave Power-to-Frequency Transduction via Injection Pulling of a Self-Sustained Oscillator for Rydberg Superheterodyne Sensing
par: Arumugam, Darmindra
Publié: (2026)

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations
par: Zhou, Xinyun, et autres
Publié: (2025)

SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
par: Masoud, Aiman Al, et autres
Publié: (2026)

Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks
par: He, Pengfei, et autres
Publié: (2024)

Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
par: Lin, Bo, et autres
Publié: (2025)

Script Sensitivity: Benchmarking Language Models on Unicode, Romanized and Mixed-Script Sinhala
par: Rajapakse, Minuri, et autres
Publié: (2026)

Enhancing the Vigenère Cipher for Unicode Compatibility: A Modern Approach to Polyalphabetic Encryption
par: Ajogbeje, Olumide Chris
Publié: (2025)

Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language Models
par: Daniel, Johan S, et autres
Publié: (2024)

GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
par: Kargaran, Amir Hossein, et autres
Publié: (2026)

DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
par: Zhang, Feiyuan, et autres
Publié: (2025)

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion
par: Zhang, Sheng, et autres
Publié: (2025)

BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
par: Rondelli, Massimo, et autres
Publié: (2026)

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
par: Rayhan, Naheed, et autres
Publié: (2026)

Optimizing Retrieval for RAG via Reinforcement Learning
par: Zhou, Jiawei, et autres
Publié: (2025)

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
par: Bochkov, A.
Publié: (2025)

Security and Detectability Analysis of Unicode Text Watermarking Methods Against Large Language Models
par: Hellmeier, Malte
Publié: (2025)

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
par: Zhou, Jiawei, et autres
Publié: (2025)

Empirical Analysis of Pull Requests for Google Summer of Code
par: Popoola, Saheed
Publié: (2024)

Visual Memory Injection Attacks for Multi-Turn Conversations
par: Schlarmann, Christian, et autres
Publié: (2026)

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
par: Pathade, Chetan
Publié: (2025)

Pulling Together or Pulling Apart?
Publié: (2020)

GrepRAG: An Empirical Study and Optimization of Grep-Like Retrieval for Code Completion
par: Wang, Baoyi, et autres
Publié: (2026)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
par: Shairah, Harethah Abu, et autres
Publié: (2025)