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.
Flexible hardware-enabled guarantees for AI compute
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes zkVM-based protocol for verifiable frontier AI pre-training with committed specs, network observations, Merkle commitments, and FP precompiles, estimating 36-month POC at single-digit overhead.
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.
-
Zero knowledge verification for frontier AI training is possible
Proposes zkVM-based protocol for verifiable frontier AI pre-training with committed specs, network observations, Merkle commitments, and FP precompiles, estimating 36-month POC at single-digit overhead.