Lucene search
+L

168 matches found

Kitploit
Kitploit
•added 2026/11/17 9:58 p.m.•8 views

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:...

6.2AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 4:15 p.m.•38 views

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...

6.4AI score
SaveExploits0References1
NVD
NVD
•added 2026/11/10 9:17 p.m.•7 views

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...

7.5CVSS0.00394EPSS
SaveExploits0References1
NVD
NVD
•added 2026/11/10 9:17 p.m.•6 views

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...

7.5CVSS0.00394EPSS
SaveExploits0References1
Mend
Mend
•added 2026/11/10 9:07 p.m.•8 views

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...

7.1CVSS6AI score0.00394EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/11/10 9:07 p.m.•29 views

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...

0.00394EPSS
SaveExploits0References1
CVE
CVE
•added 2026/11/10 9:07 p.m.•10 views

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 ...

7.5CVSS6AI score0.00394EPSS
SaveExploits0References1
EUVD
EUVD
•added 2026/11/10 9:07 p.m.•9 views

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...

6AI score0.00394EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/11/10 9:05 p.m.•33 views

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...

0.00394EPSS
SaveExploits0References1
CVE
CVE
•added 2026/11/10 9:05 p.m.•12 views

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 ...

7.5CVSS6AI score0.00394EPSS
SaveExploits0References1
EUVD
EUVD
•added 2026/11/10 9:05 p.m.•10 views

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...

6AI score0.00394EPSS
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/11/10 12:00 a.m.•6 views

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...

6.1AI score0.00394EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/11/10 12:00 a.m.•7 views

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...

6.1AI score0.00394EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
•added 2026/10/26 12:00 a.m.•18 views

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...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/25 12:00 a.m.•18 views

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...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/24 12:00 a.m.•16 views

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...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/21 12:00 a.m.•18 views

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...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/05 12:00 a.m.•14 views

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...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/05 12:00 a.m.•19 views

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...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/03 12:00 a.m.•23 views

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...

5.9AI score
SaveExploits0
Rows per page
Query Builder