RAGSieve

RAGSieve Código para RAGSieve: Detecting Knowledge-Poisoned Documents in RAG Without a Trusted Reference. RAGSieve detecta documentos con envenenamiento de conocimiento en dos puntos de un sistema de generación aumentada por recuperación RAG. RSQ es un filtro en línea: puntúa los cinco documentos...

Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement

Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy compliance. This paper presents Agentic AI based zero trust architecture Agentic-ZTA that...

Bounded Provisional Visibility: Controlling Poisoning Exposure in Continuously Ingested RAG Vector Stores

Continuous ingestion can expose new retrieval-augmented generation RAG content to retrieval before vetting completes, creating a temporal attack surface that conventional admission decisions do not capture. We present a fail-closed provisional-visibility protocol that admits new content under a...

Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate

Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermark...

LENS: The Sum Is Worse Than the Parts for Set-Level Poisoning in Retrieval-Augmented Generation

Retrieval-augmented generation RAG aggregates evidence from multiple external documents, yet this joint integration creates an underexamined vulnerability: attack effects absent in individual documents can emerge through set-level composition. Existing coordinated attacks do not explicitly enforc...

Backdoor in the Loop: Compromising Agentic Search Via Malicious Retrievers

Agentic retrieval-augmented generation RAG interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an agent observes and its subsequent search decisions. We study retriever backdoors that exploit this feedback loop and repurpose weak backdoor...

Divide and Doubt: Diverse Distributed Poisoning for Retrieval-Augmented Generation

Multi-passage corpus poisoning often repeats one target claim across similar documents, creating correlated lexical and semantic patterns that similarity- and conflict-aware defenses can suppress jointly. We introduce DnD Divide and Doubt, a targeted attack based on two principles: distributing...

RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-Specific Refutation

Retrieval augmented generation RAG systems have emerged as the dominant architecture for grounding large language model LLM outputs in verifiable external knowledge, yet their structural reliance on a dynamic retrieval pipeline introduces a largely unexplored class of adversarial vulnerability...

CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence

Cyber threat intelligence CTI is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. The harness side of this shift has matured rapidly planning loops, tool protocols, context management, but the corpus side has not: threat reports a...

Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence

Mapping cyber threat intelligence CTI text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making...

PURPOSE: Poisoning Conflict Resolution in RAG Via Proxy-Fact-Grounded Updates

In Retrieval-Augmented Generation RAG, post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target...

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM...

From Backlog Items to Security Guidance: Towards Continuous Security Compliance

Continuous software engineering in regulated domains requires engineering teams to address security throughout the development lifecycle. Yet making security requirements explicit in backlog items is still problematic. Engineers must instead infer security relevance of backlog items from brief,...

PYSEC-2026-2710 Open WebUI has Knowledge Base Destruction and RAG Poisoning via Unauthorized Collection Overwrite

Knowledge Base Destruction and RAG Poisoning via Unauthorized Collection Overwrite Affected Component Retrieval web/YouTube processing endpoints: - backend/openwebui/routers/retrieval.py lines 1810-1837, processweb - backend/openwebui/routers/retrieval.py the parallel processyoutube endpoint -...

PYSEC-2026-2729 Open WebUI has Unauthorized File and Knowledge Base Content Access via RAG Vector Search

Unauthorized File and Knowledge Base Content Access via RAG Vector Search Affected Component RAG source resolution in chat completion pipeline: - backend/openwebui/retrieval/utils.py lines 963-965, 1063-1068, 1126-1131 in getsourcesfromitems Affected Versions Current main branch commit 6fdd19bf1...

EUVD-2026-42976

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...

CVE-2026-57476 Deloitte AI Assist for Customer unauthenticated RAG corpus read and write

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...

CVE-2026-57476 Deloitte AI Assist for Customer unauthenticated RAG corpus read and write

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...

CVE-2026-57476

CVE-2026-57476 describes a vulnerability in Deloitte AI Assist for Customer where unauthenticated API endpoints allowed an attacker knowing specific parameters to read from or inject content into the retrieval-augmented generation (RAG) corpus. The issue was mitigated on 2026-03-25 by restricting...

CVE-2026-57476

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...