MLOps Under Attack: Threat Modeling Modern AI Systems - Sandeep Singh
Nullcon Goa 2025 · Main Stage
Sandeep Singh's Nullcon talk, "MLOps Under Attack: Threat Modeling Modern AI Systems," provides a crucial examination of the often-overlooked security landscape surrounding modern Machine Learning Operations (MLOps). The presentation delves beyond the surface-level concerns of Large Language Models (LLMs) to explore the entire lifecycle of AI system development, from data ingestion and model training to deployment and monitoring. Singh emphasizes that while the MLOps domain is rapidly evolving, its security posture remains in a nascent stage, presenting significant attack surfaces and vulnerabilities that traditional cybersecurity approaches may not fully address.
AI review
Competent survey of MLOps attack surface that correctly identifies the right targets — Pickle deserialization, platform CVEs in MLflow/Selden/Kubeflow, supply chain via Hugging Face, misconfigured IAM — but stops at the survey layer. No original research, no first-hand CVE work, no live exploitation; the speaker is synthesizing JFrog, Wiz, ReversingLabs, and X-Force findings, not presenting his own.