Mechanisms · category
Remote & side-channel sensing
Inferring activity from outside or from physical signals: detecting data centres, classifying workloads from power or other emissions.
| Name | Type | Readiness | Verifies | Threat model |
|---|---|---|---|---|
| On-chip telemetry from timing, memory and performance counters Uses timing, memory-residency and performance-counter signals measured on AI accelerators as evidence about which workloads they are running. | Mechanism | R2Demonstrated | This compute runs inference, not training; Declared hardware is idle or shut down | Semi-trusted prover |
| Workload classification from telemetry and side channels Telling whether chips are training, serving or doing non-AI work from GPU counters or power draw, signals that do not read weights or data. | Mechanism | R2Demonstrated | This compute runs inference, not training | Adversarial prover |
| Remote detection of data centres Remote detection locates large data centres and estimates their power capacity without site access, using satellite imagery, heat signatures and public records such as permits. | Mechanism | R1Proposed | There is no undeclared relevant compute | Adversarial prover |
Includes records that list this as a secondary category.