# Adversarial Attacks on AI-Generated Text Detection Models: A Token Probability-Based Approach Using Embeddings

arXiv: https://arxiv.org/abs/2501.18998 · HTML: https://mlsanity.com/paper/2501.18998/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 31 Jan 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (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)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [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)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling](https://mlsanity.com/paper/1312.3005/) (2013)
- [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)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [TweepFake: about Detecting Deepfake Tweets](https://mlsanity.com/paper/2008.00036/) (2020)
- [word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method](https://mlsanity.com/paper/1402.3722/) (2014)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic](https://mlsanity.com/paper/1804.01508/) (2018)
- [ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing](https://mlsanity.com/paper/2303.13367/) (2023)
- [Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization with Medical Applications](https://mlsanity.com/paper/1809.04547/) (2018)
- [Coalesced Multi-Output Tsetlin Machines with Clause Sharing](https://mlsanity.com/paper/2108.07594/) (2021)
- [Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling](https://mlsanity.com/paper/2009.04861/) (2020)
- [Tsetlin Machine Embedding: Representing Words Using Logical Expressions](https://mlsanity.com/paper/2301.00709/) (2023)
- [A Short Review of Ethical Challenges in Clinical Natural Language Processing](https://mlsanity.com/paper/1703.10090/) (2017)
- [Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size](https://mlsanity.com/paper/2301.08190/) (2023)
- [ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection](https://mlsanity.com/paper/2402.11167/) (2024)
- [Exploring State Space and Reasoning by Elimination in Tsetlin Machines](https://mlsanity.com/paper/2407.09162/) (2024)

## Built on by (most cited first, 5 of 5)

- [DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution](https://mlsanity.com/paper/2512.04838/) (2025)
- [Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations](https://mlsanity.com/paper/2510.02319/) (2025)
- [Transforming Chatbot Text: A Sequence-to-Sequence Approach](https://mlsanity.com/paper/2506.12843/) (2025)
- [Interpretable Predictability-Based AI Text Detection: A Replication Study](https://mlsanity.com/paper/2603.15034/) (2026)
- [FastOmniTMAE: Parallel Clause Learning for Scalable and Hardware-Efficient Tsetlin Embeddings](https://mlsanity.com/paper/2605.06982/) (2026)

## Abstract (arXiv)

In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services to enhance their capabilities in identifying AI-generated content. Adversarial attacks are often used to test the robustness of AI-text generated detectors. This work proposes a novel textual adversarial attack on the detection models such as Fast-DetectGPT. The method employs embedding models for data perturbation, aiming at reconstructing the AI generated texts to reduce the likelihood of detection of the true origin of the texts. Specifically, we employ different embedding techniques, including the Tsetlin Machine (TM), an interpretable approach in machine learning for this purpose. By combining synonyms and embedding similarity vectors, we demonstrates the state-of-the-art reduction in detection scores against Fast-DetectGPT. Particularly, in the XSum dataset, the detection score decreased from 0.4431 to 0.2744 AUROC, and in the SQuAD dataset, it dropped from 0.5068 to 0.3532 AUROC.