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 proposes TRIP-RAG, a dynamic anonymization framework that selectively anonymizes sensitive entities in knowledge bases used for RAG, significantly improving utility while maintaining strong…

This paper proposes PA-HDP, a framework for privacy-preserving retrieval-augmented generation using prompt-aware dynamic hierarchical differential privacy.

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…

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are…

The paper introduces PAS, a structured privacy mechanism that encodes user location using relative anchors, enabling location privacy in spatial RAG systems while maintaining high retrieval performanc…

Trans-RAG introduces a novel query-centric vector transformation technique to enable secure, efficient, and accurate cross-organizational retrieval in RAG systems without plaintext decryption.

A multi-agent framework is proposed to sanitize retrieved content in Retrieval-Augmented Generation while preserving semantic core and reducing privacy leakage.

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…

This case study systematically measures how placing anonymization at different points (dataset vs. generated answer) within the RAG pipeline affects the privacy-utility trade-off, demonstrating that p…

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

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

SEAL-Tag is a privacy-preserving runtime environment that mitigates PII leakage in Retrieval-Augmented Generation (RAG) systems by enforcing verifiable evidence aggregation and structured auditing.

The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data di…

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 introduces RAGAL, a retrieval-augmented assistant for technical support teams, built under three constraints: zero data egress, read-only, and limited resources. The highest-leverage invest…

The paper introduces 'Routing Hijacking,' a severe attack where malicious clients forge semantic profiles in Federated RAG systems to misroute target queries, and proposes a trust-aware post-routing f…