# TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles

arXiv: https://arxiv.org/abs/2309.12934 · HTML: https://mlsanity.com/paper/2309.12934/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection](https://mlsanity.com/paper/2305.14902/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [Do Language Models Plagiarize?](https://mlsanity.com/paper/2203.07618/) (2022)
- [Stylometric Detection of AI-Generated Text in Twitter Timelines](https://mlsanity.com/paper/2303.03697/) (2023)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [On the effectiveness of persistent homology](https://mlsanity.com/paper/2206.10551/) (2022)
- [Acceptability Judgements via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2205.09630/) (2022)
- [Whodunit? Learning to Contrast for Authorship Attribution](https://mlsanity.com/paper/2209.11887/) (2022)
- [The Topological BERT: Transforming Attention into Topology for Natural Language Processing](https://mlsanity.com/paper/2206.15195/) (2022)
- [SynSciPass: detecting appropriate uses of scientific text generation](https://mlsanity.com/paper/2209.03742/) (2022)
- [J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News](https://mlsanity.com/paper/2309.03164/) (2023)
- [Topological Analysis of Syntactic Structures](https://mlsanity.com/paper/1903.05181/) (2019)
- [Topological Data Analysis for Speech Processing](https://mlsanity.com/paper/2211.17223/) (2022)
- [Dialogue Term Extraction using Transfer Learning and Topological Data Analysis](https://mlsanity.com/paper/2208.10448/) (2022)
- [Persistent Topology of Syntax](https://mlsanity.com/paper/1507.05134/) (2015)

## Built on by (most cited first, 10 of 10)

- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution](https://mlsanity.com/paper/2504.11369/) (2025)
- [Topological Data Analysis Applications in Natural Language Processing: A Survey](https://mlsanity.com/paper/2411.10298/) (2024)
- [Who Wrote the Book? Detecting and Attributing LLM Ghostwriters](https://mlsanity.com/paper/2603.28054/) (2026)
- [Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach](https://mlsanity.com/paper/2506.20197/) (2025)
- [Better Call Claude: Can LLMs Detect Changes of Writing Style?](https://mlsanity.com/paper/2508.00680/) (2025)
- [Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling](https://mlsanity.com/paper/2604.25860/) (2026)
- [Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems](https://mlsanity.com/paper/2507.21157/) (2025)
- [Optimizing Soft Prompt Tuning via Structural Evolution](https://mlsanity.com/paper/2602.16500/) (2026)
- [T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting](https://mlsanity.com/paper/2607.14113/) (2026)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have enabled the generation of open-ended high-quality texts, that are non-trivial to distinguish from human-written texts. We refer to such LLM-generated texts as deepfake texts. There are currently over 72K text generation models in the huggingface model repo. As such, users with malicious intent can easily use these open-sourced LLMs to generate harmful texts and dis/misinformation at scale. To mitigate this problem, a computational method to determine if a given text is a deepfake text or not is desired--i.e., Turing Test (TT). In particular, in this work, we investigate the more general version of the problem, known as Authorship Attribution (AA), in a multi-class setting--i.e., not only determining if a given text is a deepfake text or not but also being able to pinpoint which LLM is the author. We propose TopFormer to improve existing AA solutions by capturing more linguistic patterns in deepfake texts by including a Topological Data Analysis (TDA) layer in the Transformer-based model. We show the benefits of having a TDA layer when dealing with imbalanced, and multi-style datasets, by extracting TDA features from the reshaped pooledoutput of our backbone as input. This Transformer-based model captures contextual representations (i.e., semantic and syntactic linguistic features), while TDA captures the shape and structure of data (i.e., linguistic structures). Finally, TopFormer, outperforms all baselines in all 3 datasets, achieving up to 7% increase in Macro F1 score. Our code and datasets are available at: https://github.com/AdaUchendu/topformer