pith. sign in

WAVE : Workload-aware verification via performance-counter evidence for GPU inference

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Detecting Hidden ML Training With Zero-Overhead Telemetry

cs.LG · 2026-06-17 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Detecting Hidden ML Training With Zero-Overhead Telemetry cs.LG · 2026-06-17 · unverdicted · none · ref 73

    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.