# Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models

arXiv: https://arxiv.org/abs/2511.02894 · HTML: https://mlsanity.com/paper/2511.02894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 22 of its 66 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Label Sanitization against Label Flipping Poisoning Attacks](https://mlsanity.com/paper/1803.00992/) (2018)
- [Data Poisoning Attacks on Federated Machine Learning](https://mlsanity.com/paper/2004.10020/) (2020)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [Protecting Sensory Data against Sensitive Inferences](https://mlsanity.com/paper/1802.07802/) (2018)
- [LLMSense: Harnessing LLMs for High-level Reasoning Over Spatiotemporal Sensor Traces](https://mlsanity.com/paper/2403.19857/) (2024)
- [Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2409.01980/) (2024)
- [LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution](https://mlsanity.com/paper/2312.09007/) (2023)
- [Large Language Models are Zero-Shot Recognizers for Activities of Daily Living](https://mlsanity.com/paper/2407.01238/) (2024)
- [Efficient Prompting for LLM-based Generative Internet of Things](https://mlsanity.com/paper/2406.10382/) (2024)
- [Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and Challenges](https://mlsanity.com/paper/2407.07196/) (2024)
- [Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System](https://mlsanity.com/paper/2208.08433/) (2022)
- [Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks](https://mlsanity.com/paper/2403.02983/) (2024)
- [Wi-Chat: Large Language Model Powered Wi-Fi Sensing](https://mlsanity.com/paper/2502.12421/) (2025)
- [LightLLM: A Versatile Large Language Model for Predictive Light Sensing](https://mlsanity.com/paper/2411.15211/) (2024)
- [Leveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation](https://mlsanity.com/paper/2503.16622/) (2025)
- [Are You Being Tracked? Discover the Power of Zero-Shot Trajectory Tracing with LLMs!](https://mlsanity.com/paper/2403.06201/) (2024)
- [Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning](https://mlsanity.com/paper/2407.09958/) (2024)
- [EgoLog: Ego-Centric Fine-Grained Daily Log with Ubiquitous Wearables](https://mlsanity.com/paper/2504.02624/) (2025)

## Abstract (arXiv)

The widespread integration of wearable sensing devices in Internet of Things (IoT) ecosystems, particularly in healthcare, smart homes, and industrial applications, has required robust human activity recognition (HAR) techniques to improve functionality and user experience. Although machine learning models have advanced HAR, they are increasingly susceptible to data poisoning attacks that compromise the data integrity and reliability of these systems. Conventional approaches to defending against such attacks often require extensive task-specific training with large, labeled datasets, which limits adaptability in dynamic IoT environments. This work proposes a novel framework that uses large language models (LLMs) to perform poisoning detection and sanitization in HAR systems, utilizing zero-shot, one-shot, and few-shot learning paradigms. Our approach incorporates textitrole play prompting, whereby the LLM assumes the role of expert to contextualize and evaluate sensor anomalies, and textitthink step-by-step reasoning, guiding the LLM to infer poisoning indicators in the raw sensor data and plausible clean alternatives. These strategies minimize reliance on curation of extensive datasets and enable robust, adaptable defense mechanisms in real-time. We perform an extensive evaluation of the framework, quantifying detection accuracy, sanitization quality, latency, and communication cost, thus demonstrating the practicality and effectiveness of LLMs in improving the security and reliability of wearable IoT systems.