ai-exploits

AI エクスプロイト AIの世界にはセキュリティ問題が存在します。それはChatGPTなどのLLMへの入力だけに限りません。Protect AIおよびHuntrバグ報奨金プラットフォーム上の独立したセキュリティ専門家による調査に基づくと、機械学習モデルの構築、トレーニング、デプロイに使用されるツール、ライブラリ、フレームワークに対する、よりインパクトが大きく実用的な攻撃が数多く存在します。これらの攻撃の多くは、認証を必要とせずにシステム全体の乗っ取りや、機密データ、モデル、認証情報の損失につながります。 このリポジトリの公開により、Protect...

llm-guard

!WARNING THIS PROJECT HAS BEEN ARCHIVED. This project and its associated models on Hugging Face are no longer under active development or maintained. LLM Guard - The Security Toolkit for LLM Interactions LLM Guard by Protect AI is a comprehensive tool designed to fortify the security of Large...

CVE-2026-77557

A malicious actor with access to the network could exploit an Improper Access Control vulnerability found in UniFi Protect AI Key to escalate privileges on the device...

CVE-2026-77557

A malicious actor with access to the network could exploit an Improper Access Control vulnerability found in UniFi Protect AI Key to escalate privileges on the device...

CVE-2026-77557

CVE-2026-77557 is a critical (CVSS 9.8) Improper Access Control vulnerability in UniFi Protect AI Key . A malicious actor with network access can exploit it to escalate privileges on the device, with no prior authentication required (PR:N). The attack vector is network-based with low complexity, ...

Researchers Uncover Vulnerabilities in Open-Source AI and ML Models

A little over three dozen security vulnerabilities have been disclosed in various open-source artificial intelligence AI and machine learning ML models, some of which could lead to remote code execution and information theft. The flaws, identified in tools like ChuanhuChatGPT, Lunary, and LocalAI...