Model Namespace Reuse Turns a Trusted Name Into a Supply-Chain Redirect
Unit 42 showed that a deleted Hugging Face author namespace, or a transferred model whose former author namespace later becomes reclaimable, can leave stale references pointing to a name another party can register. In controlled tests, researchers reclaimed abandoned namespaces, recreated expected model paths, and made Vertex AI and Azure AI Foundry deployments load reverse-shell models. The original publisher account was not compromised. Defenders should bind deployments to immutable digests and signers, monitor namespace lifecycles, mirror approved artifacts internally, and isolate model loading.
Why it relates: Stale, unpinned model references resolve to an adversarial source and the replacement executes in downstream deployed endpoints. A deleted or transferred model namespace is reused while downstream catalogs retain an unpinned author/model reference. The same historical identifier then resolves to an attacker’s replacement, defeating traceability from the approved model reference to its current producer and bytes. The evidenced gap is model-asset identity and version provenance at reference resolution and admission. The source does not establish that the organizations lack an entire governance program, accountable personnel or regulatory documentation.
Unit 42 researchers demonstrated an AI supply chain attack in which an attacker reclaims a deleted Hugging Face author namespace and publishes a malicious model under the same historical Author/ModelName identifier. Applications and model catalogs that retain unpinned references to that identifier may resolve and deploy the adversary-controlled replacement rather than the originally trusted artifact. The attack can affect deleted models and models whose ownership was transferred to a new Hugging Face author. In the ownership-transfer scenario, Hugging Face redirects requests for the old path to the new model location, allowing stale references to continue working. If the original author namespace is later deleted and reclaimed by an attacker, the attacker can recreate the old path and cause it to resolve to a malicious model instead of the legitimate redirected model. Unit 42 demonstrated this technique against Hugging Face-backed model catalogs in Google Vertex AI and Azure AI Foundry. The researchers embedded reverse-shell payloads in replacement models and obtained code execution in the deployed endpoint environments. They also identified reusable model references in open-source code repositories, documentation, default arguments, example notebooks, and downstream model registries, which could expose users who do not directly interact with Hugging Face.
AIA · Read the full case ↗ · SecureFlow · Read the full case ↗