Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators

TL;DR

This paper investigates whether advanced AI language models like GPT-2 can generate texts that deceive online authorship attribution systems, revealing potential vulnerabilities in author identification methods used in digital forensics.

Contribution

It demonstrates that current neural text generators can effectively mimic individual author styles to deceive authorship attribution models.

Findings

AI-generated texts can successfully mimic authorial style

Current AA models can be deceived by GPT-2 generated texts

Implications for spam detection and forensic investigations

Abstract

Recently, there has been a rise in the development of powerful pre-trained natural language models, including GPT-2, Grover, and XLM. These models have shown state-of-the-art capabilities towards a variety of different NLP tasks, including question answering, content summarisation, and text generation. Alongside this, there have been many studies focused on online authorship attribution (AA). That is, the use of models to identify the authors of online texts. Given the power of natural language models in generating convincing texts, this paper examines the degree to which these language models can generate texts capable of deceiving online AA models. Experimenting with both blog and Twitter data, we utilise GPT-2 language models to generate texts using the existing posts of online users. We then examine whether these AI-based text generators are capable of mimicking authorial style to such a degree that they can deceive typical AA models. From this, we find that current AI-based text generators are able to successfully mimic authorship, showing capabilities towards this on both datasets. Our findings, in turn, highlight the current capacity of powerful natural language models to generate original online posts capable of mimicking authorial style sufficiently to deceive popular AA methods; a key finding given the proposed role of AA in real world applications such as spam-detection and forensic investigation.