Detecting Hidden ML Training With Zero-Overhead Telemetry

• URL: http://arxiv.org/abs/2606.19262v1
• Date: Wed, 17 Jun 2026 16:39:40 GMT
• Title: Detecting Hidden ML Training With Zero-Overhead Telemetry
• Abstract summary: Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable.<n>We evaluate the adversarial robustness of GPU workload classification using only zero-overhead, privacy-preserving NVML telemetry.<n>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.
• Score: 0.5633936331890176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Workload Identification with Physical Side Channels for AI Governance [0.5013248430919224]
  We show that an external observer can identify the class of the workload running on an NVIDIA H200 from its power draw.<n>Four evasion strategies are tested to disguise training as inference, producing an additional 680 adversarial traces.
  arXiv  Detail & Related papers  (2026-08-31T19:59:35Z)
• Detecting Object Tracking Failure via Sequential Hypothesis Testing [80.7891291021747]
  Real-time online object tracking in videos constitutes a core task in computer vision.<n>We propose interpreting object tracking as a sequential hypothesis test, wherein evidence for or against tracking failures is gradually accumulated over time.<n>We propose both supervised and unsupervised variants by leveraging either ground-truth or solely internal tracking information.
  arXiv  Detail & Related papers  (2026-02-13T14:57:15Z)
• Timing and Memory Telemetry on GPUs for AI Governance [3.3108773921973316]
  We introduce a measurement framework that generates timing and memory-based observables that correlate with compute activity.<n>These primitives provide statistical and behavioral indicators of GPU engagement that remain observable even without trusted firmware, enclaves, or vendor-controlled counters.
  arXiv  Detail & Related papers  (2026-02-10T03:20:06Z)
• Hybrid Cryptographic Monitoring System for Side-Channel Attack Detection on PYNQ SoCs [0.0]
  AES-128 encryption is theoretically secure but vulnerable in practical deployments due to timing and fault injection attacks on embedded systems.<n>This work presents a lightweight dual-detection framework combining statistical thresholding and machine learning (ML) for real-time anomaly detection.
  arXiv  Detail & Related papers  (2025-08-29T13:13:43Z)
• Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems [5.99333254967625]
  This paper proposes a hybrid framework that integrates machine learning (ML) and natural language explanations (LLMs) to detect cyberattacks.<n>The proposed framework effectively real-time detection with interpretable, high-fidelity explanations, addressing a critical need for actionable AI in smart grid cybersecurity.
  arXiv  Detail & Related papers  (2025-07-29T21:23:08Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning [61.10299147201369]
  This paper introduces a novel autonomous RL approach, called DigiRL, for training in-the-wild device control agents. We build a scalable and parallelizable Android learning environment equipped with a VLM-based evaluator. We demonstrate the effectiveness of DigiRL using the Android-in-the-Wild dataset, where our 1.3B VLM trained with RL achieves a 49.5% absolute improvement.
  arXiv  Detail & Related papers  (2024-06-14T17:49:55Z)
• Deep Learning-based Embedded Intrusion Detection System for Automotive CAN [12.084121187559864]
  Various intrusion detection approaches have been proposed to detect and tackle such threats, with machine learning models proving highly effective. We propose a hybrid FPGA-based ECU approach that can transparently integrate IDS functionality through a dedicated off-the-shelf hardware accelerator. Our results show that the proposed approach provides an average accuracy of over 99% across multiple attack datasets with 0.64% false detection rates.
  arXiv  Detail & Related papers  (2024-01-19T13:13:38Z)
• GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks [73.88590165742721]
  We propose a novel adversarial training technique that exploits auxiliary tasks under a limited set of training data. Our approach extends single-task models into multi-task models during the min-max optimization of adversarial training. We demonstrate that guided multi-task learning is an actionable and promising avenue to push further the boundaries of model robustness.
  arXiv  Detail & Related papers  (2023-02-06T16:23:24Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.