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 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 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 PopQuiz Attack is a novel black-box membership inference attack that successfully tests whether large language models memorize specific training data by framing the target data as multiple-choice…

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…

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

The paper introduces a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while…

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

ImageAuditor introduces a novel Membership Inference Attack (MIA) specifically designed for Image-based Retrieval-Augmented Generation (IRAG) systems, achieving high accuracy by addressing cross-modal…

The paper introduces CYBERMASKQA, a novel privacy-aware benchmark designed to evaluate Large Language Models' ability to perform accurate cybersecurity question answering while simultaneously preservi…

The paper proposes a new evaluation framework showing that, under realistic conditions, Membership Inference Attacks (MIAs) are weak privacy threats, suggesting that relying on them as a primary priva…

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…

The paper introduces AURA, an LLM-powered mask-reconstruct framework, to improve text anonymization by enhancing resistance to agentic web-search re-identification while better preserving contextual u…

The paper introduces AURA, an LLM-powered mask-reconstruct framework, to improve text anonymization by enhancing resistance to agentic web-search re-identification while better preserving contextual u…

The paper proposes Multi-Recall Memory MIA (MRMMIA), a unified attack framework to test for privacy leakage by determining if a candidate memory unit belongs to a chat agent's private memory store.

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…

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…