# huggingface
12 artikelengetagd met “huggingface”
smolagents-security-analyse
Security-analyse van Hugging Face smolagents, inclusief code-uitvoeringsrisico's en vertrouwensgrenzen voor tools.
Beveiliging van Hugging Face Inference Endpoints
Security analysis of Hugging Face Inference Endpoints including model isolation and API security.
Model Supply Chain Risks
Attack vectors in the AI model supply chain, including malicious model files, pickle exploits, compromised model registries, and dependency vulnerabilities.
AI Supply Chain Exploitation
Methodologie voor het uitbuiten van de AI/ML-supply-chain: RCE via modelserialisatie, dependency confusion, datasetvergiftiging, CI/CD-injectie en container escape.
AI-supply-chain: een diepe duik
Diepgaande analyse van security-dreigingen in de AI-supply-chain, waaronder sleeper agents, slopsquatting, kwaadaardige modeluploads, pickle-deserialisatie-exploits en uitdagingen bij de verificatie van modelherkomst.
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.
Walkthrough: beveiligingsaudit van Hugging Face
Step-by-step walkthrough for auditing Hugging Face models: scanning for malicious model files, verifying model provenance, assessing model card completeness, and testing Spaces and Inference API security.
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.
Walkthroughs van cloud-AI-platforms
Hands-on walkthroughs for red teaming AI systems deployed on major cloud platforms: AWS Bedrock, Azure OpenAI, Google Vertex AI, and Hugging Face Hub.
Door Hugging Face gehoste modellen testen
Red team testing guide for models hosted on Hugging Face including Inference API and Spaces.