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

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

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 systematically evaluates advanced retrieval-augmented generation (RAG) architectures for Cyber Threat Intelligence (CTI), demonstrating that a hybrid graph-text approach significantly improv…

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 LeakDojo, a framework that systematically evaluates RAG leakage risks, finding that stronger LLM instruction-following and query generation are major independent contributors to d…

RefineRAG introduces a novel word-level poisoning framework that significantly enhances knowledge poisoning attacks against RAG systems, achieving state-of-the-art effectiveness and transferability to…

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…

The paper introduces Oracle Poisoning, an attack that corrupts knowledge graphs used by AI agents, demonstrating that all tested models blindly trust poisoned data at high sophistication levels.

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…

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

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…

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 systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…

This paper systematically maps the expanded attack surface of agentic AI systems, identifying new threat vectors like RAG poisoning and cross-agent manipulation, and proposes a comprehensive security…

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…