Issues

[framework-update] MITRE ATLAS — content change detected

GenAI-Security-Project/crosswalk#357 · opened

on Nov 2, 2026

[new-cve] CVE-2026-117574 — A flaw was found in ai-gateway-payload-processing. An authenticated remote attac

GenAI-Security-Project/crosswalk#356 · opened

on Nov 2, 2026

[new-cve] CVE-2026-116692 — MLflow is an open source AI engineering platform for agents, large language mode

GenAI-Security-Project/crosswalk#355 · opened

on Nov 2, 2026

[new-cve] CVE-2026-116691 — MLflow is an open source AI engineering platform for agents, large language mode

GenAI-Security-Project/crosswalk#354 · opened

on Nov 2, 2026

[new-cve] CVE-2026-116690 — MLflow is an open source AI engineering platform for agents, large language mode

GenAI-Security-Project/crosswalk#353 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115917 — vLLM is an inference and serving engine for large language models. Prior to 0.32

GenAI-Security-Project/crosswalk#351 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115918 — vLLM is an inference and serving engine for large language models. From 0.16.0 u

GenAI-Security-Project/crosswalk#352 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115915 — vLLM is an inference and serving engine for large language models. Prior to 0.32

GenAI-Security-Project/crosswalk#349 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115916 — vLLM is an inference and serving engine for large language models. Prior to 0.32

GenAI-Security-Project/crosswalk#350 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115913 — vLLM is an inference and serving engine for large language models. Prior to 0.32

GenAI-Security-Project/crosswalk#347 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115914 — vLLM is an inference and serving engine for large language models. From 0.11.1 u

GenAI-Security-Project/crosswalk#348 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115912 — vLLM is an inference and serving engine for large language models. Prior to 0.32

GenAI-Security-Project/crosswalk#346 · opened

on Nov 2, 2026

[new-cve] CVE-2026-115911 — vLLM is an inference and serving engine for large language models. From 0.19.0 u

GenAI-Security-Project/crosswalk#345 · opened

on Nov 2, 2026

[new-research] arXiv:2610.39899 — ExploreRepair: Evidence-Specialized Agents for Vulnerability Repair under Inform

GenAI-Security-Project/crosswalk#344 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40742 — Prevented is Not Protected: What Attack Success Rate Hides about RAG

GenAI-Security-Project/crosswalk#342 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40735 — RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functi

GenAI-Security-Project/crosswalk#343 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40744 — CLIC: Closed-Loop Intent Consistency for Securing LLM-Driven Control in Open RAN

GenAI-Security-Project/crosswalk#341 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40753 — "Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents

GenAI-Security-Project/crosswalk#340 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40396 — Understanding and Mitigating Role Spoofing in LLMs

GenAI-Security-Project/crosswalk#339 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40543 — The Privacy and Security Risks of Edge LLM Optimization

GenAI-Security-Project/crosswalk#338 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40913 — Coupled or Independent? Fault Coupling in Agentic Medical Vision Systems

GenAI-Security-Project/crosswalk#336 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40613 — TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Ra

GenAI-Security-Project/crosswalk#337 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40981 — Towards Elastic Least Privilege for Agent Planning

GenAI-Security-Project/crosswalk#334 · opened

on Nov 2, 2026

[new-research] arXiv:2610.40975 — Does Showing Agents the Privilege of Their Tools Reduce Over-Privileged Tool Sel

GenAI-Security-Project/crosswalk#335 · opened

on Nov 2, 2026

[new-research] arXiv:2610.41039 — Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-o

GenAI-Security-Project/crosswalk#333 · opened

on Nov 2, 2026

Navigation Menu

Repository navigation

Issues

[framework-update] MITRE ATLAS — content change detected

[new-cve] CVE-2026-117574 — A flaw was found in ai-gateway-payload-processing. An authenticated remote attac

[new-cve] CVE-2026-116692 — MLflow is an open source AI engineering platform for agents, large language mode

[new-cve] CVE-2026-116691 — MLflow is an open source AI engineering platform for agents, large language mode

[new-cve] CVE-2026-116690 — MLflow is an open source AI engineering platform for agents, large language mode

[new-cve] CVE-2026-115917 — vLLM is an inference and serving engine for large language models. Prior to 0.32

[new-cve] CVE-2026-115918 — vLLM is an inference and serving engine for large language models. From 0.16.0 u

[new-cve] CVE-2026-115915 — vLLM is an inference and serving engine for large language models. Prior to 0.32

[new-cve] CVE-2026-115916 — vLLM is an inference and serving engine for large language models. Prior to 0.32

[new-cve] CVE-2026-115913 — vLLM is an inference and serving engine for large language models. Prior to 0.32

[new-cve] CVE-2026-115914 — vLLM is an inference and serving engine for large language models. From 0.11.1 u

[new-cve] CVE-2026-115912 — vLLM is an inference and serving engine for large language models. Prior to 0.32

[new-cve] CVE-2026-115911 — vLLM is an inference and serving engine for large language models. From 0.19.0 u

[new-research] arXiv:2610.39899 — ExploreRepair: Evidence-Specialized Agents for Vulnerability Repair under Inform

[new-research] arXiv:2610.40742 — Prevented is Not Protected: What Attack Success Rate Hides about RAG

[new-research] arXiv:2610.40735 — RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functi

[new-research] arXiv:2610.40744 — CLIC: Closed-Loop Intent Consistency for Securing LLM-Driven Control in Open RAN

[new-research] arXiv:2610.40753 — "Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents

[new-research] arXiv:2610.40396 — Understanding and Mitigating Role Spoofing in LLMs

[new-research] arXiv:2610.40543 — The Privacy and Security Risks of Edge LLM Optimization

[new-research] arXiv:2610.40913 — Coupled or Independent? Fault Coupling in Agentic Medical Vision Systems

[new-research] arXiv:2610.40613 — TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Ra

[new-research] arXiv:2610.40981 — Towards Elastic Least Privilege for Agent Planning

[new-research] arXiv:2610.40975 — Does Showing Agents the Privilege of Their Tools Reduce Over-Privileged Tool Sel

[new-research] arXiv:2610.41039 — Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-o