# Detecting Hidden ML Training With Zero-Overhead Telemetry

arXiv: https://arxiv.org/abs/2606.19262 · HTML: https://mlsanity.com/paper/2606.19262/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Computing Power and the Governance of Artificial Intelligence](https://mlsanity.com/paper/2402.08797/) (2024)
- [What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring](https://mlsanity.com/paper/2303.11341/) (2023)
- [Electricity Demand and Grid Impacts of AI Data Centers: Challenges and Prospects](https://mlsanity.com/paper/2509.07218/) (2025)
- [Training Compute Thresholds: Features and Functions in AI Regulation](https://mlsanity.com/paper/2405.10799/) (2024)
- [Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment](https://mlsanity.com/paper/2507.15916/) (2025)
- [Governing Through the Cloud: The Intermediary Role of Compute Providers in AI Regulation](https://mlsanity.com/paper/2403.08501/) (2024)
- [Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel](https://mlsanity.com/paper/2109.07395/) (2021)
- [Hardware-Enabled Mechanisms for Verifying Responsible AI Development](https://mlsanity.com/paper/2505.03742/) (2025)
- [An International Agreement to Prevent the Premature Creation of Artificial Superintelligence](https://mlsanity.com/paper/2511.10783/) (2025)
- [Flexible Hardware-Enabled Guarantees for AI Compute](https://mlsanity.com/paper/2506.15093/) (2025)
- [The MIT Supercloud Workload Classification Challenge](https://mlsanity.com/paper/2204.05839/) (2022)
- [Detecting Covert Cryptomining using HPC](https://mlsanity.com/paper/1909.00268/) (2019)
- [Exploiting HDMI and USB Ports for GPU Side-Channel Insights](https://mlsanity.com/paper/2410.02539/) (2024)

## Built on by (most cited first, 4 of 4)

- [Traccia: An OpenTelemetry-Based Governance Platform for AI Systems](https://mlsanity.com/paper/2607.14309/) (2026)
- [Privacy-Preserving AI Verification via Minimal Information Disclosure](https://mlsanity.com/paper/2608.02774/) (2026)
- [Workload Identification with Physical Side Channels for AI Governance](https://mlsanity.com/paper/2609.00309/) (2026)
- [Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance](https://mlsanity.com/paper/2610.07476/) (2026)

## Abstract (arXiv)

Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable. We evaluate the adversarial robustness of GPU workload classification using only zero-overhead, privacy-preserving NVML telemetry: content-agnostic signals that observe physical effects of computation without accessing model weights, training data, or hyperparameters. Across 5 rounds of monitor-evader iteration, we evaluate 20 evasion strategy families on 9 GPU models spanning 4 architecture generations. We develop a classifier that achieves 98.2% binary accuracy at identifying training workloads across the whole corpus, and 43-87% accuracy against the most challenging unexpected workloads even when they are adversarially disguised.