Timing and Memory Telemetry on GPUs for AI Governance

This research paper introduces a measurement framework for monitoring GPU utilization in untrusted environments to support AI governance. The framework uses four complementary primitives based on timing and memory characteristics—Proof-of-Work-inspired mechanisms, Verifiable Delay Functions, GEMM-based tensor-core measurements, and VRAM-residency tests—to detect GPU compute activity even without trusted firmware or vendor-controlled counters. The approach aims to provide compute-based telemetry that can help detect unauthorized repurposing of GPUs for model training or policy violations.