# 4M Models Scanned: Protect AI + Hugging Face 6 Months In

DevFeed: [4M Models Scanned: Protect AI + Hugging Face 6 Months In](<https://devfeed.tech/articles/4m-models-scanned-protect-ai-hugging-face-6-months-in-7434.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/pai-6-month>)

Author: Sean Morgan

Published: 2025-04-14T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Machine Learning, Security Attacks](<https://devfeed.tech/topics/machine-learning-security-attacks.md>), [Threat Research](<https://devfeed.tech/topics/threat-research.md>), [Security](<https://devfeed.tech/topics/security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [obfuscation](<https://devfeed.tech/topics/obfuscation.md>), [vulnerability](<https://devfeed.tech/topics/vulnerability.md>), [payload](<https://devfeed.tech/topics/payload.md>), [Script](<https://devfeed.tech/topics/script.md>), [llamafile](<https://devfeed.tech/topics/llamafile.md>), [Tensorflow](<https://devfeed.tech/topics/tensorflow.md>)

Tags: [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [hub](<https://devfeed.tech/tags/hub.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [keras](<https://devfeed.tech/tags/keras.md>), [llamafile](<https://devfeed.tech/tags/llamafile.md>), [obfuscation](<https://devfeed.tech/tags/obfuscation.md>), [partnerships](<https://devfeed.tech/tags/partnerships.md>), [payload](<https://devfeed.tech/tags/payload.md>), [security](<https://devfeed.tech/tags/security.md>), [tensorflow](<https://devfeed.tech/tags/tensorflow.md>), [threat-detection](<https://devfeed.tech/tags/threat-detection.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [zero-trust](<https://devfeed.tech/tags/zero-trust.md>)

## AI overview

Hugging Face and Protect AI report six months of collaboration on Guardian, a scanning system that improves security checks for models hosted on the Hugging Face Hub. Guardian added four detection modules, expanded format and obfuscation coverage, identified a Keras vulnerability, and provides inline alerts and vulnerability reports. The system uses a zero trust approach that treats arbitrary code execution as unsafe, including code hidden through obfuscation.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.