2026-09-25 –, Ladd Room (Capacity 170)
As organizations adopt Large Language Models in production systems, a critical gap is emerging: model trust and supply chain security.
Unlike container ecosystems, where image signing, scanning, and provenance are well-established practices, LLM artifacts are often downloaded, shared, and deployed with minimal verification. This creates a blind spot in modern AI infrastructure where untrusted or tampered models can be introduced into production environments.
In this talk, we explore how cloud-native security practices can be extended to AI workloads using tools like Sigstore and Clair.
We will cover:
- Signing and verifying LLM artifacts to ensure provenance and integrity
- Scanning model containers for vulnerabilities and unsafe dependencies
- Building a trusted supply chain for AI artifacts
- Integrating model verification into CI/CD and deployment pipelines
Through practical examples and workflows, this session demonstrates how teams can apply existing container security principles to AI systems without introducing entirely new infrastructure.
The goal is to make LLM deployment as trustworthy as container deployment already is today.
Shubhra Deshpande is a software engineer working on large-scale cloud-native infrastructure and developer platforms. She focuses on building reliable, production-grade systems that sit at the intersection of distributed systems, DevOps, and emerging AI workloads.
Her work spans platform engineering, container ecosystems, and operationalizing machine learning systems in real-world environments. She is particularly interested in how existing cloud-native primitives can be reused to simplify the lifecycle of modern AI systems.
