Imagen de Portada

Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cui, Huining, Liu, Wei
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Databases
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Defense against Poisoning Attacks under Shuffle-DP
por: Wang, Siyi, et al.
Publicado: (2026)

PACE: Poisoning Attacks on Learned Cardinality Estimation
por: Zhang, Jintao, et al.
Publicado: (2024)

Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs
por: He, Xi, et al.
Publicado: (2024)

SecReEvalBench: A Multi-turned Security Resilience Evaluation Benchmark for Large Language Models
por: Cui, Huining, et al.
Publicado: (2025)

FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation
por: Zhao, Dongfang
Publicado: (2024)

RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement
por: Wang, Ziye, et al.
Publicado: (2026)

Chain Table: Protecting Table-Level Data Integrity by Digital Ledger Technology
por: Yu, Feng, et al.
Publicado: (2025)

DP-S4S: Accurate and Scalable Select-Join-Aggregate Query Processing with User-Level Differential Privacy
por: Qiu, Yuan, et al.
Publicado: (2026)

Blockchain-based vs. SQL Database Systems for Digital Twin Evidence Management: A Comparative Forensic Analysis
por: Franken, Boyd, et al.
Publicado: (2025)

Acyclic Graph Pattern Counting under Local Differential Privacy
por: Hu, Yihua, et al.
Publicado: (2026)

Polars inside Intel SGX2 Enclaves: An Empirical Study of Confidential Analytical Query Processing
por: Wang, Wei, et al.
Publicado: (2026)

NSHEDB: Noise-Sensitive Homomorphic Encrypted Database Query Engine
por: Jung, Boram, et al.
Publicado: (2026)

Secure Query Processing with Linear Complexity
por: Luo, Qiyao, et al.
Publicado: (2024)

A General Framework for Per-record Differential Privacy
por: Chen, Xinghe, et al.
Publicado: (2025)

FHE-SQL: Fully Homomorphic Encrypted SQL Database
por: Tseng, Po-Yu, et al.
Publicado: (2025)

Enhanced Privacy Bound for Shuffle Model with Personalized Privacy
por: Liu, Yixuan, et al.
Publicado: (2024)

Sketches-based join size estimation under local differential privacy
por: Zhang, Meifan, et al.
Publicado: (2024)

Towards Privacy-Preserving Range Queries with Secure Learned Spatial Index over Encrypted Data
por: Wang, Zuan, et al.
Publicado: (2025)

LAPRAS : Learning-Augmented PRivate Answering for linear query Streams
por: Mundra, Pranay, et al.
Publicado: (2026)

ThreatKG: An AI-Powered System for Automated Open-Source Cyber Threat Intelligence Gathering and Management
por: Gao, Peng, et al.
Publicado: (2022)

From Randomized Response to Randomized Index: Answering Subset Counting Queries with Local Differential Privacy
por: Ye, Qingqing, et al.
Publicado: (2025)

Verifiable, Efficient and Confidentiality-Preserving Graph Search with Transparency
por: Wang, Qiuhao, et al.
Publicado: (2025)

Femur: A Flexible Framework for Fast and Secure Querying from Public Key-Value Store
por: Zhang, Jiaoyi, et al.
Publicado: (2025)

A Comprehensive Survey of Blockchain Scalability: Shaping Inner-Chain and Inter-Chain Perspectives
por: Chen, Baochao, et al.
Publicado: (2024)

Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval
por: Wu, Hao, et al.
Publicado: (2025)

Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption
por: Wang, William Zerong, et al.
Publicado: (2025)

CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
por: Li, Chunyang, et al.
Publicado: (2025)

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
por: Zhao, Tianzhe, et al.
Publicado: (2025)

Fast Private Adaptive Query Answering for Large Data Domains
por: Fuentes, Miguel, et al.
Publicado: (2026)

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database
por: Do, Luat, et al.
Publicado: (2026)

PROTECT-DB: Protecting Data using Replicated State Machines: Efficient Corruption Detection & Recovery
por: Utgikar, Anant, et al.
Publicado: (2026)

Interpreting the Error of Differentially Private Median Queries through Randomization Intervals
por: Humphries, Thomas, et al.
Publicado: (2026)

Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
por: Li, Hanxi, et al.
Publicado: (2026)

Oblivis: A Framework for Delegated and Efficient Oblivious Transfer
por: Abadi, Aydin, et al.
Publicado: (2026)

Descriptor: Multi-Regional Cloud Honeypot Dataset (MURHCAD)
por: Feito-Casares, Enrique, et al.
Publicado: (2026)

Confidential Databases Without Cryptographic Mappings
por: Huang, Wenxuan, et al.
Publicado: (2026)

RADAR: Exposing Unlogged NoSQL Operations
por: Nissan, Mahfuzul I., et al.
Publicado: (2026)

TableMark: A Multi-bit Watermark for Synthetic Tabular Data
por: Xia, Yuyang, et al.
Publicado: (2026)

GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy
por: Sun, Haochen, et al.
Publicado: (2025)