A classifier using NVML telemetry identifies ML training workloads at 98.2% accuracy and retains 43-87% accuracy against the strongest tested adversarial evasions across 9 GPUs and 5 iteration rounds.
Hardware-enabled mechanisms for verifying responsible AI development
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Bounded performance metrics always favor convergence of AI capabilities to meek models while unbounded metrics allow frontier models to maintain leads indefinitely, with policy implications for capability concentration.
citing papers explorer
-
Detecting Hidden ML Training With Zero-Overhead Telemetry
A classifier using NVML telemetry identifies ML training workloads at 98.2% accuracy and retains 43-87% accuracy against the strongest tested adversarial evasions across 9 GPUs and 5 iteration rounds.
-
Two AI Metrics Diverged: Will it Make All the Difference?
Bounded performance metrics always favor convergence of AI capabilities to meek models while unbounded metrics allow frontier models to maintain leads indefinitely, with policy implications for capability concentration.