paper-with-me

홈 › Papers

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

2022-03-18 · Keenan Jones, Jason R. C. Nurse, Shujun Li

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.

📄 PDF Abstract BibTeX arXiv:2203.09813

Code (0)

등록된 구현이 없습니다.

Tasks

Authorship AttributionQuestion AnsweringSpam detectionText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

CCTAA: A Reproducible Corpus for Chinese Authorship Attribution Research

2022-06-01 · LREC 2022 6 · Haining Wang, Allen Riddell

Authorship attribution infers the likely author of an unsigned, single-authored document from a pool of candidates. Despite recent advances, a lack of standard, reproducible testbeds for Chinese language documents impede…

Authorship Attribution

The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution

2021-11-01 · Findings (EMNLP) 2021 11 · Malik Altakrori, Jackie Chi Kit Cheung, Benjamin C. M. Fung

Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors. Researchers have investigated same-topic and cross-topic scenarios of authorship attrib…

Authorship Attribution

The Topic Confusion Task: A Novel Scenario for Authorship Attribution

2021-04-17 · Malik H. Altakrori, Jackie Chi Kit Cheung, Benjamin C. M. Fung

Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors. Researchers have investigated same-topic and cross-topic scenarios of authorship attrib…

Authorship Attribution

I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution

2025-06-18 · Tamas Bisztray, Bilel Cherif, Richard A. Dubniczky, Nils Gruschka 외

Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identifying the specific model behind each sam…

Authorship AttributionBinary ClassificationDecoder

Mode Effects' Challenge to Authorship Attribution

2021-04-01 · EACL 2021 2 · Haining Wang, Allen Riddell, Patrick Juola

The success of authorship attribution relies on the presence of linguistic features specific to individual authors. There is, however, limited research assessing to what extent authorial style remains constant when indiv…

Authorship AttributionFeature EngineeringSentence