# When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection

arXiv: https://arxiv.org/abs/2510.12476 · HTML: https://mlsanity.com/paper/2510.12476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics](https://mlsanity.com/paper/1812.08092/) (2018)
- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning](https://mlsanity.com/paper/2410.20964/) (2024)
- [Personalized Generation In Large Model Era: A Survey](https://mlsanity.com/paper/2503.02614/) (2025)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective](https://mlsanity.com/paper/2502.14296/) (2025)
- [People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text](https://mlsanity.com/paper/2501.15654/) (2025)
- [Fundamental Limits and Tradeoffs in Invariant Representation Learning](https://mlsanity.com/paper/2012.10713/) (2020)
- [Training-free LLM-generated Text Detection by Mining Token Probability Sequences](https://mlsanity.com/paper/2410.06072/) (2024)
- [Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection](https://mlsanity.com/paper/2310.02861/) (2023)

## Built on by (most cited first, 1 of 1)

- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no prior work has examined personalized machine-generated text (MGT) detection. In this paper, we introduce dataset, the first benchmark for evaluating detector robustness in personalized settings, built from literary and blog texts paired with their LLM-generated imitations. Our experimental results demonstrate large performance gaps across detectors in personalized settings: some state-of-the-art models suffer significant drops. We attribute this limitation to the textitfeature-inversion trap, where features that are discriminative in general domains become inverted and misleading when applied to personalized text. Based on this finding, we propose method, a simple and reliable way to predict detector performance changes in personalized settings. method identifies latent directions corresponding to inverted features and constructs probe datasets that differ primarily along these features to evaluate detector dependence. Our experiments show that method can accurately predict both the direction and the magnitude of post-transfer changes, showing 85% correlation with the actual performance gaps. We hope that this work will encourage further research on personalized text detection.