168 matches found
signed-but-steerable
Signed but Steerable: the text-vector integrity gap in offline RAG Code, data and results for the paper Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation G. Feretzakis, A. Papaspyridis, securagen.ai. Archived on Zenodo:...
RAGSieve
RAGSieve Code for RAGSieve: Detecting Knowledge-Poisoned Documents in RAG Without a Trusted Reference. RAGSieve detects knowledge-poisoning documents at two points in a retrieval-augmented generation RAG system. RSQ is an online filter: it scores the five documents selected for generation against...
CVE-2026-108167
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
CVE-2026-107372
The auth0-ai-js FGA retriever does not distinguish between authorization checks under different conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the generated response...
CVE-2026-108167
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
CVE-2026-108167
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
CVE-2026-108167
The auth0-ai-python FGA retriever is vulnerable to an incorrect authorization issue (CWE-863). The component fails to distinguish between authorization checks across different users, relations, or conditions when filtering documents during retrieval-augmented generation . Consequently, documents ...
EUVD-2026-122933
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
CVE-2026-107372
The auth0-ai-js FGA retriever does not distinguish between authorization checks under different conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the generated response...
CVE-2026-107372
The auth0-ai-js FGA retriever contains an incorrect authorization vulnerability (CWE-863 ). The component fails to distinguish between authorization checks under different conditions when filtering documents during retrieval-augmented generation . This flaw allows documents that should be denied ...
EUVD-2026-122931
The auth0-ai-js FGA retriever does not distinguish between authorization checks under different conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the generated response...
CVE-2026-108167: Auth0: The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations,…
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
PT-2026-144737
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the...
GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation
Retrieval-Augmented Generation RAG enhances the factual grounding of Large Language Models LLMs by incorporating external evidence, but also exposes them to corpus poisoning attacks. In particular, coordinated attacks can introduce multiple mutually reinforcing poisoned documents into retrieved...
Factual yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation
The stance expressed in responses from retrieval-augmented generation systems is significantly influenced by the stance distribution of the retrieved materials. Existing research on knowledge poisoning has primarily targeted factual errors. In contrast, this study focuses on injection attacks in...
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Generative AI and large language models LLMs are moving into the Internet of Things, yet most deployments assume cloud connectivity, and many IoT settings have intermittent, restricted, or no connectivity. We propose a connectivity-regime framework C0-C4, a taxonomy of inference-time trust...
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
Retrieval-augmented generation RAG systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection. Yet RAG protection studies use incompatible evaluation metrics, datasets, and threat models. We prese...
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...
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...
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...