Cover Image

Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Minseok, Lee, Hankook, Koo, Hyungjoon
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Information Retrieval D.4.6; K.6.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fool Me If You Can: On the Robustness of Binary Code Similarity Detection Models against Semantics-preserving Transformations
by: Uhm, Jiyong, et al.
Published: (2026)

UnPII: Unlearning Personally Identifiable Information with Quantifiable Exposure Risk
by: Jeon, Intae, et al.
Published: (2026)

Post-quantum Federated Learning: Secure And Scalable Threat Intelligence For Collaborative Cyber Defense
by: Nayak, Prabhudarshi, et al.
Published: (2026)

RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks
by: Chakraborty, Amit, et al.
Published: (2025)

vCause: Efficient and Verifiable Causality Analysis for Cloud-based Endpoint Auditing
by: Song, Qiyang, et al.
Published: (2026)

Dynamic Vulnerability Patching for Heterogeneous Embedded Systems Using Stack Frame Reconstruction
by: Zhou, Ming, et al.
Published: (2025)

SpyChain: Multi-Vector Supply Chain Attacks on Small Satellite Systems
by: Vanlyssel, Jack, et al.
Published: (2025)

ARMOUR US: Android Runtime Zero-permission Sensor Usage Monitoring from User Space
by: Long, Yan, et al.
Published: (2025)

Memory Forensics Techniques for Automated Detection and Analysis of Go Malware
by: Ali, Hala, et al.
Published: (2026)

The Discovery, Disclosure, and Investigation of CVE-2024-25825
by: Chasens, Hunter
Published: (2025)

Silent Consent, Persistent Risk: Android Permission Groups and Custom Permissions
by: Akanji, Olawale Amos, et al.
Published: (2026)

SAFE-SiP: Secure Authentication Framework for System-in-Package Using Multi-party Computation
by: Tashdid, Ishraq, et al.
Published: (2025)

Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
by: Collu, Matteo Gioele, et al.
Published: (2023)

The Need for Standardized Evidence Sampling in CMMC Assessments: A Survey-Based Analysis of Assessor Practices
by: Therrien, Logan, et al.
Published: (2026)

CryptoGuard: Lightweight Hybrid Detection and Response to Host-based Cryptojackers in Linux Cloud Environments
by: Park, Gyeonghoon, et al.
Published: (2025)

ZTD$_{JAVA}$: Mitigating Software Supply Chain Vulnerabilities via Zero-Trust Dependencies
by: Amusuo, Paschal C., et al.
Published: (2023)

Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs
by: Mosievskiy, Nikita
Published: (2026)

Static Attribution of Android Residential Proxy Malware Using Graph Kernels
by: Clark, Peter, et al.
Published: (2026)

SecureBank: A Financially-Aware Zero Trust Architecture for High-Assurance Banking Systems
by: Biao, Paulo Fernandes
Published: (2025)

Predicting Known Vulnerabilities from Attack Descriptions Using Sentence Transformers
by: Othman, Refat
Published: (2026)

Broken Object Level Authorization in the Wild: An Empirical Taxonomy from 100+ Bug Bounty Disclosures
by: Kaur, Bandana
Published: (2026)

AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
by: Dawson, Ads, et al.
Published: (2025)

Privacy-Enhancing Encryption in Data Sharing: A Survey on Security, Performance and Functionality
by: Lv, Yongyang, et al.
Published: (2026)

Witnessd: Proof-of-process via Adversarial Collapse
by: Condrey, David
Published: (2026)

The Automation Advantage in AI Red Teaming
by: Mulla, Rob, et al.
Published: (2025)

Unified Framework for Qualifying Security Boundary of PUFs Against Machine Learning Attacks
by: Fei, Hongming, et al.
Published: (2026)

Firmware Distribution as Attack Surface: A Security Study of ASIC Cryptocurrency Miners
by: Pouliquen, Pierre, et al.
Published: (2026)

Rhea: Detecting Privilege-Escalated Evasive Ransomware Attacks Using Format-Aware Validation in the Cloud
by: Kim, Beom Heyn, et al.
Published: (2026)

LEMIX: Enabling Testing of Embedded Applications as Linux Applications (Extended Report)
by: Tanksalkar, Sai Ritvik, et al.
Published: (2025)

A Secure, Manifest-Based Framework for Delegated Privilege Promotion
by: Chowdhury, Rajarshi, et al.
Published: (2026)

quantum-safe: Bridging the Post-Quantum Production Gap with a Hybrid-by-Default Python Cryptography Library
by: Shaw, Animesh
Published: (2026)

EXHIB: A Benchmark for Realistic and Diverse Evaluation of Function Similarity in the Wild
by: Fan, Yiming, et al.
Published: (2026)

Post-Quantum Discovery as a Governance Capability: Evidence-Based Cryptographic Visibility and Exposure Prioritisation in a Critical Service Provider
by: Zelenovic, Jelena, et al.
Published: (2026)

The Birthmark Standard: Privacy-Preserving Photo Authentication via Hardware Roots of Trust and Consortium Blockchain
by: Ryan, Sam
Published: (2026)

ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems
by: Chitan, Florin Adrian
Published: (2026)

SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots
by: Adebimpe, Adetayo, et al.
Published: (2025)

SecureSign: Bridging Security and UX in Mobile Web3 through Emulated EIP-6963 Sandboxing
by: Ji, Charles Cheng, et al.
Published: (2025)

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning
by: Huff, Philip, et al.
Published: (2026)

AITH: A Post-Quantum Continuous Delegation Protocol for Human-AI Trust Establishment
by: Chen, Zhaoliang
Published: (2026)

AegisShield: Democratizing Cyber Threat Modeling with Generative AI
by: Grofsky, Matthew
Published: (2025)