Where every claim in SecProve
comes from.

Open-source project for signing, verifying, and protecting software supply chains. Keyless signing for artifacts.

Bug bounty platform focused on AI/ML vulnerabilities. Real-world vulnerability data in ML frameworks and models. Good for grounding tool security questions in actual discovered vulnerabilities.

Seminal backdoor attack paper. Demonstrated trojaned models in transfer learning scenarios. Foundational for AI supply chain security questions.

Hugging Face's safe serialization format for ML models. Prevents arbitrary code execution from pickle-based attacks.

The largest model hub. Security features: malware scanning, pickle scanning, safetensors format. Questions on model provenance, serialization risks (pickle exploits), and model marketplace trust.

Security best practices for using Hugging Face Hub — model scanning, SafeTensors, access controls, and supply chain considerations.

Discovered 100+ malicious models on Hugging Face exploiting pickle deserialization for code execution. Real-world evidence of AI supply chain attacks. Good for scenario-based questions.

Extending software bill of materials concepts to AI: model cards, data cards, training provenance. Emerging standard for AI supply chain transparency.

Framework for ensuring the integrity of software artifacts throughout the supply chain. Applicable to ML model pipelines.

Top 10 security risks specific to machine learning systems, including supply chain attacks, data poisoning, and model theft.

Security audit firm with deep AI/ML expertise. Published research on pickle deserialization attacks, model file format security, and ML pipeline vulnerabilities. Technical depth from a security-first perspective.