EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific contextualization. However, it also introduces new attack surfaces such as corpus poisoning at the same time. Most of the existing defense methods rely on the internal knowledge of the model, which conflicts with the design concept of RAG. To bridge the gap, EcoSafeRAG uses sentence-level processing and bait-guided context diversity detection to identify malicious content by analyzing the context diversity of candidate documents without relying on LLM internal knowledge. Experiments show EcoSafeRAG delivers state-of-the-art security with plug-and-play deployment, simultaneously improving clean-scenario RAG performance while maintaining practical operational costs (relatively 1.2$\times$ latency, 48\%-80\% token reduction versus Vanilla RAG).
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityRAGRetrievalRetrieval-augmented GenerationSentenceToken ReductionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Retrieval-Augmented LLMs for Security Incident Analysis
Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection alerts, network traffic records, and authentication events. This process is labor-…
Intrusion DetectionAdapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation
Security applications are increasingly relying on large language models (LLMs) for cyber threat detection; however, their opaque reasoning often limits trust, particularly in decisions that require domain-specific cybers…
RAG for Effective Supply Chain Security Questionnaire Automation
In an era where digital security is crucial, efficient processing of security-related inquiries through supply chain security questionnaires is imperative. This paper introduces a novel approach using Natural Language Pr…
ManagementRAGRetrievalRetrieval-augmented GenerationVulCPE: Context-Aware Cybersecurity Vulnerability Retrieval and Management
The dynamic landscape of cybersecurity demands precise and scalable solutions for vulnerability management in heterogeneous systems, where configuration-specific vulnerabilities are often misidentified due to inconsisten…
ManagementRelation ExtractionRetrievalSecurity and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling retrieval mechanisms with generative models, RAG systems improve factual gr…