Imagen de Portada

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jin, Weifei, Wang, Xilong, Zou, Wei, Jia, Jinyuan, Gong, Neil
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
por: Zou, Wei, et al.
Publicado: (2024)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
por: Zou, Wei, et al.
Publicado: (2025)

PDFInspect: A Unified Feature Extraction Framework for Malicious Document Detection
por: P, Sharmila S
Publicado: (2026)

Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classification
por: Li, Yujie, et al.
Publicado: (2024)

TracLLM: A Generic Framework for Attributing Long Context LLMs
por: Wang, Yanting, et al.
Publicado: (2025)

Provably Robust Federated Reinforcement Learning
por: Fang, Minghong, et al.
Publicado: (2025)

MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification
por: Luo, Xiang, et al.
Publicado: (2025)

WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT
por: Tian, Ye, et al.
Publicado: (2025)

Toward More Generalized Malicious URL Detection Models
por: Tsai, YunDa, et al.
Publicado: (2022)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
por: Zhang, Jinghuai, et al.
Publicado: (2022)

GraphRAG under Fire
por: Liang, Jiacheng, et al.
Publicado: (2025)

GasTrace: Detecting Sandwich Attack Malicious Accounts in Ethereum
por: Liu, Zekai, et al.
Publicado: (2024)

Malicious Internet Entity Detection Using Local Graph Inference
por: Mandlik, Simon, et al.
Publicado: (2024)

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
por: Yin, Chenlong, et al.
Publicado: (2026)

Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation
por: Hassan, Shayan Ali, et al.
Publicado: (2026)

Competitive Advantage Attacks to Decentralized Federated Learning
por: Jia, Yuqi, et al.
Publicado: (2023)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
por: Liu, Yupei, et al.
Publicado: (2023)

Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection
por: Liang, Zhihong, et al.
Publicado: (2025)

From Past to Present: A Survey of Malicious URL Detection Techniques, Datasets and Code Repositories
por: Tian, Ye, et al.
Publicado: (2025)

Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates
por: Yue, Kai, et al.
Publicado: (2025)

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
por: Jia, Yuqi, et al.
Publicado: (2026)

A Consensus-Bayesian Framework for Detecting Malicious Activity in Enterprise Directory Access Graphs
por: Uppuluri, Pratyush, et al.
Publicado: (2026)

Graph Neural Network Explanations are Fragile
por: Li, Jiate, et al.
Publicado: (2024)

ML Study of MaliciousTransactions in Ethereum
por: Katz, Natan
Publicado: (2024)

Certifiably Robust Image Watermark
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

Toward Malicious Clients Detection in Federated Learning
por: Dou, Zhihao, et al.
Publicado: (2025)

Malicious URL Detection using optimized Hist Gradient Boosting Classifier based on grid search method
por: Maftoun, Mohammad, et al.
Publicado: (2024)

One Detector Fits All: Robust and Adaptive Detection of Malicious Packages from PyPI to Enterprises
por: Montaruli, Biagio, et al.
Publicado: (2025)

FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
por: Zhang, Jianyi, et al.
Publicado: (2025)

A New Dataset and Methodology for Malicious URL Classification
por: Schvartzman, Ilan, et al.
Publicado: (2024)

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
por: Suri, Anshuman, et al.
Publicado: (2025)

Multi-Agent Systems Execute Arbitrary Malicious Code
por: Triedman, Harold, et al.
Publicado: (2025)

Towards Quantum Machine Learning for Malicious Code Analysis
por: Lopez, Jesus, et al.
Publicado: (2025)

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
por: Jin, Weifei, et al.
Publicado: (2025)

Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
por: Liu, Yinuo, et al.
Publicado: (2025)

Stealing Training Graphs from Graph Neural Networks
por: Lin, Minhua, et al.
Publicado: (2024)

Detecting Malicious AI Agents Through Simulated Interactions
por: Pi, Yulu, et al.
Publicado: (2025)

Learned-Database Systems Security
por: Schuster, Roei, et al.
Publicado: (2022)

RobPI: Robust Private Inference against Malicious Client
por: Xue, Jiaqi, et al.
Publicado: (2026)

Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
por: Mozaffari, Hamid, et al.
Publicado: (2024)