RAGShield introduces a novel, pattern-based defense system that accurately detects subtle numerical claim manipulation in government RAG systems, overcoming the inherent blind spot of embedding-based…

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

CleanBase is a method that detects malicious documents in RAG knowledge databases by identifying clusters (cliques) of documents that exhibit unusually high semantic similarity.

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 demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

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

TextSeal is a novel, non-overhead, and robust watermark for LLMs that enables accurate provenance tracking and detection of unauthorized use even after model distillation.

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

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 proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting i…

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 RADAR, a novel graph-based framework that dynamically defends Retrieval-Augmented Generation (RAG) systems against evolving adversarial attacks while minimizing storage overhead.

The paper proposes Adaptive Stealing (AS), a novel and more robust watermark stealing algorithm that dynamically selects optimal attack perspectives to significantly increase the efficiency of comprom…

The paper introduces WaveGuard, a frequency-aware, single-pass defense framework that safeguards text-to-image models by injecting structured, imperceptible perturbations into generated images, thereb…