# model-hub
5 artikelengetagd met “model-hub”
Injection van kwaadaardige adapters
How attackers craft LoRA adapters containing backdoors, distribute poisoned adapters through model hubs, and exploit adapter stacking to compromise model safety -- techniques, detection challenges, and real-world supply chain risks.
Beveiliging van Hugging Face Hub
Attack surface analysis of Hugging Face Hub: malicious model uploads, pickle deserialization exploits, model card manipulation, trust signal limitations, gated model bypass, and community-driven trust exploitation.
Supply chain-aanval op de model hub
Attacking the ML model supply chain through hub repositories like Hugging Face, including typosquatting, model poisoning, and repository manipulation techniques.
Beveiligingstesten van HuggingFace Spaces
End-to-end walkthrough for security testing HuggingFace Spaces applications: Space enumeration, Gradio/Streamlit exploitation, API endpoint testing, secret management review, and model access control assessment.
Hugging Face Hub Red Team-walkthrough
Walkthrough voor het beoordelen van AI-modellen op Hugging Face Hub: beveiligingsassessment van modellen, scannen op kwaadaardige modellen, testen met de Transformers-library, en evaluatie van Spaces-applicaties.