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…

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 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…

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…

This paper introduces a novel privacy mechanism, the geometry-aware Mahalanobis norm planar Laplace (MNPL) mechanism, to provide formal location privacy guarantees for channel charting used in locatio…

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…

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.

The paper demonstrates a class of steganographic exfiltration attacks against vector databases by hiding data within embeddings, and proposes VectorPin, a cryptographic provenance protocol to detect s…

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…

This paper identifies two novel location inference attacks against k-nearest neighbor queries (kNNQ) and proposes DPRS, a differential privacy framework that effectively protects location privacy whil…

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 local private information retrieval (local PIR), redefining user privacy in graph-replicated systems to focus on hiding the message index from servers, and demonstrates that local…

This paper demonstrates that standard privacy guarantees for multi-tenant RAG services fail when multiple accounts from the same tenant collude, proposing a novel audit protocol to quantify this joint…

The paper proposes DAMPER, a domain-aware framework that autonomously extracts and rewrites private information from text while providing rigorous differential privacy guarantees, significantly improv…

This paper demonstrates that retrieval-augmented in-context learning systems for document QA are vulnerable to membership inference attacks, proposing novel black-box methods that exploit query prefix…

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…

BRASP is a searchable encryption scheme that enables private Boolean range queries over encrypted spatial data while robustly protecting both the search pattern and access pattern.

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…

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…

The paper introduces MosaicLeaks, a benchmark demonstrating that deep research agents querying external sources can leak private information from their local documents, and proposes PA-DR to mitigate…