openfree's picture

openfree

openfree

AI & ML interests

Contact: arxivgpt@gmail.com

Recent Activity

liked a Space about 2 hours ago
FINAL-Bench/ViKernel-Scanner
reacted to SeaWolf-AI's post with šŸ”„ about 2 hours ago
šŸ›”ļø We handed 20 open models a shell. 20 of them ran a dangerous command. ViKernel Scanner is a free AI model security scanner. It hands a model 8 mock tools (files, mail, web, shell, payments), sends 100 attack checks plus 20 normal-work controls, and records every tool call the model tries to make. It scores what a model does, not what it says. Reference scans of 20 widely used open-weight models through the Hugging Face router: • 20 of 20 graded F • The median model attempted a dangerous action in 40 of 100 checks • Plain and disguised commands (base64, hex, ROT13, reversed text, quote breaks) reached the shell tool With ViKernel Firewall placed inside the model weights, 897 of 897 dangerous calls were denied before execution. The firewall judges the action, not the words, and because it lives in the weights it cannot be quietly removed. Any OpenAI-compatible endpoint (Hugging Face router, OpenRouter, OpenAI, Anthropic, Gemini, Together, Groq, your own vLLM). About a minute per model, graded A to F. Open source, clone it, run it locally. Read the full results: https://huggingface.co/blog/FINAL-Bench/we-handed-20-open-models-a-shell-20-of-them-failed Scan your model: https://huggingface.co/spaces/FINAL-Bench/ViKernel-Scanner Source (Apache-2.0): https://github.com/final-bench/vikernel-scanner Use the scanner on your own models, or on models you are allowed to test. #AISecurity #LLMSecurity #AIAgents #RedTeaming #PromptInjection
updated a dataset about 7 hours ago
VIDraft/press-assets
View all activity

Organizations

Blog-explorers's profile picture VIDraft's profile picture korea forestry's profile picture PowergenAI's profile picture OpenFree_AI's profile picture Gemma Challenge's profile picture JGOS's profile picture Archsloth's profile picture