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…

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 Agentic Witnessing, a TEE-enabled framework that allows external verifiers to audit the qualitative properties of private datasets by querying an LLM-based auditor without accessing…

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

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

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

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 Search-Bound Proximity Proofs (SBPP) to close an authorization provenance gap in encrypted geographic search by binding zero-knowledge proofs to specific search sessions for audit…

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…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

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…

The paper introduces CanaryRAG, a novel dual-path runtime defense mechanism that detects RAG Knowledge Base Leakage attacks by embedding canary tokens into retrieved knowledge chunks.

The paper introduces MAGMA, a novel stochastic RAG framework that enhances malware detection by quantifying epistemic uncertainty, achieving a high detection rate of 98.4% against evasion attacks.

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…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

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 addresses the vulnerability of zero-knowledge proximity proofs in stateful systems by proposing Zairn-ZKP, a method that embeds operational context (like drop identity and policy version) di…

Aegon is a new protocol that provides an auditable, tamper-evident infrastructure for tracking AI content licensing transactions and compliance receipts.