This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks acros…

The paper evaluates four RAG architectures under knowledge base poisoning, demonstrating that advanced architectures significantly improve robustness against adversarial contradictions, localizing the…

The paper proposes the Sentinel-Strategist architecture, an adaptive defense mechanism that selectively deploys security measures in Retrieval-Augmented Generation (RAG) systems to significantly reduc…

This paper introduces a novel attack, RA-ICA, that targets RAG-enhanced LLMs by poisoning external knowledge bases to drastically increase inference costs, achieving up to a 13.12x increase in token c…

The paper systematically evaluates advanced retrieval-augmented generation (RAG) architectures for Cyber Threat Intelligence (CTI), demonstrating that a hybrid graph-text approach significantly improv…

The paper introduces PIDP-Attack, a novel compound adversarial attack that combines prompt injection with database poisoning to manipulate Retrieval-Augmented Generation (RAG) systems against arbitrar…

E-MIA introduces a novel, stealthy black-box membership inference attack that converts verifiable hard evidence within a candidate document into an objective, multi-part exam score to determine if the…

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

This paper empirically evaluates the use of Retrieval-Augmented Generation (RAG) for malware explanation and finds that RAG frequently degrades explanation quality by adding noise when structured secu…

The paper proposes an unsupervised method using multiple statistical indicators to detect adversarial or compromised context documents in Retrieval Augmented Generation (RAG) systems, even without kno…

The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, ach…

The paper introduces DiscourseFlip, a novel black-box, graph-guided attack that manipulates opinions across an entire multi-topic query network, demonstrating a significant leap in scope and effective…

The paper introduces DiscourseFlip, a novel graph-guided attack that demonstrates how coordinated poisoning across a multi-topic query space can manipulate the overall opinion generated by black-box R…

The paper introduces CORDON-MAS, a compartmentalized framework that defends Retrieval-Augmented Generation (RAG) against knowledge poisoning by enforcing strict information-flow control, significantly…

The paper proposes M extsuperscript{3}Att, a knowledge-poisoning framework that injects covert misinformation into medical multimodal RAG systems using paired visual data triggers, demonstrating attac…

The paper proposes a layered, server-side isolation architecture to secure Retrieval-Augmented Generation (RAG) and agentic AI systems in multitenant enterprise environments, ensuring that retrieval a…

The paper introduces LeakDojo, a framework that systematically evaluates RAG leakage risks, finding that stronger LLM instruction-following and query generation are major independent contributors to d…

PRAG is an end-to-end privacy-preserving Retrieval-Augmented Generation (RAG) system that maintains high retrieval accuracy and scalability in cloud environments by encrypting both documents and queri…

SilentRetrieval introduces a sophisticated, two-stage data poisoning attack that successfully hijacks Retrieval-Augmented Generation (RAG) systems by injecting adversarially crafted, yet highly fluent…

The paper introduces FedRAG, a novel federated RAG framework that enables privacy-preserving cross-institutional knowledge collaboration by decoupling the self-attention mechanism from data localizati…