# On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection

Source: [On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection](<https://www.sota2.com/research/paper/6a1d1208dbd7150506f83f42>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-02T05:00:05.014Z

Authors: Gudrun Schappacher-Tilp, Nicoletta Kaehling, Jan Kornberger, Egon Teiniker

Published: 2026-05-28T20:21:52.000Z

## Abstract

Visual monitoring systems that rely on cloud-based AI inference expose raw image data to external services, creating fundamental tensions with the data-minimisation principle of the General Data Protection Regulation (GDPR). This paper presents a proof-of-concept privacy-by-design pipeline that resolves this tension by confining all inference entirely to the edge device. A YOLOv5n-seg model compiled for a Hailo-8L AI accelerator delivers real-time object detection on a Raspberry Pi 5, from which raw pixel buffers are immediately discarded after inference. A stateful trigger engine forwards minimal JSON event payloads to a locally hosted instance of Phi-3 Mini (3.8B parameters, Q4\_0 quantisation), which synthesises one-to-two sentence natural-language alerts for a human operator. No image data crosses the network boundary at any point; only the generated text alert is transmitted. We describe the full system architecture and implementation, report measured inference latency and resource utilisation on the target hardware, and present representative generated alerts. The results demonstrate that combining a dedicated neural-network accelerator with an on-device large language model on a single-board computer is not only feasible but produces practically deployable, human-readable monitoring output while aligning with GDPR Art. 5(1)(c) by design.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.30544>)

[PDF](<https://arxiv.org/pdf/2605.30544.pdf>)