Search papers, labs, and topics across Lattice.
This paper introduces an attestation-aware promotion gate to verify claims about LLM training and release pipelines, ensuring that artifacts meet security and provenance requirements before being admitted into trusted environments. The gate enforces policies related to safe loading, static scanning, and secure deployment, and can optionally integrate dynamic runtime security signals. By cryptographically binding claims to artifacts, the proposed system aims to mitigate supply-chain risks such as compromised dependencies and backdoored models.
Securing LLM supply chains requires cryptographically binding training and release claims to artifacts, enabling verifiable enforcement of security policies across teams and stages.
Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes with supply-chain risks, including compromised dependencies, malicious hub artifacts, unsafe deserialization, forged provenance, and backdoored models. A core gap is that training and release claims (e.g., data and code lineage, build environment, and security scanning results) are rarely cryptographically bound to the artifacts they describe, making enforcement inconsistent across teams and stages. We propose an attestation-aware promotion gate: before an artifact is admitted into trusted environments (training, fine-tuning, deployment), the gate verifies claim evidence, enforces safe loading and static scanning policies, and applies secure-by-default deployment constraints. When organizations operate runtime security tooling, the same gate can optionally ingest standardized dynamic signals via plugins to reduce uncertainty for high-risk artifacts. We outline a practical claims-to-controls mapping and an evaluation blueprint using representative supply-chain scenarios and operational metrics (coverage and decisions), charting a path toward a full research paper.
