Results 11 to 20 of about 276,851 (299)
Unsupervised Text Style Transfer for Authorship Obfuscation in Bahasa Indonesia
IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 2023 Authorship attribution is an NLP task to identify the author of a text based on stylometric analysis. On the other hand, authorship obfuscation aims to protect against authorship attribution by modifying a text’s style.
Yunita Sari, Fadhlan Pasyah Al Faridzi
doaj +1 more source
Automatic authorship attribution [PDF]
Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics -, 1999 In this paper we present an approach to automatic authorship attribution dealing with real-world (or unrestricted) text. Our method is based on the computational analysis of the input text using a text-processing tool. Besides the style markes relevant to the output of this tool we also use analysis-dependent style markers, that is, measures that ...
Efstathios Stamatatos +2 more
openaire +2 more sources
Neural Authorship Attribution: Stylometric Analysis on Large Language Models [PDF]
International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, 2023 Large language models (LLMs) such as GPT-4, PaLM, and Llama have significantly propelled the generation of AI-crafted text. With rising concerns about their potential misuse, there is a pressing need for AI-generated-text forensics.
Tharindu Kumarage, Huan Liu
semanticscholar +1 more source
RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation [PDF]
International Conference on Software Engineering, 2022 Source code authorship attribution is an important problem often encountered in applications such as software forensics, bug fixing, and software quality analysis.
Zhen Li +4 more
semanticscholar +1 more source
Rhythm-based authorship recognition in syllabic and accentual-syllabic verse
Literatura: Teoría, Historia, Crítica, 2023 This contribution explores the extent to which rhythm-based features of poetic texts can contribute meaningfully to authorship recognition. We show that, although a binary categorization of languages as syllabic vs.
Petr Plecháč, David J. Birnbaum
doaj +1 more source
TopFormer: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles [PDF]
European Conference on Artificial Intelligence, 2023 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.
Adaku Uchendu, Thai Le, Dongwon Lee
semanticscholar +1 more source
Using Data Compression to Build a Method for Statistically Verified Attribution of Literary Texts
Entropy, 2021 We consider the problems of the authorship of literary texts in the framework of the quantitative study of literature. This article proposes a methodology for authorship attribution of literary texts based on the use of data compressors.
Boris Ryabko, Nadezhda Savina
doaj +1 more source
Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts? [PDF]
Transactions of the Association for Computational Linguistics, 2023 Authorship verification is the task of determining if two distinct writing samples share the same author and is typically concerned with the attribution of written text.
Cristina Aggazzotti +2 more
semanticscholar +1 more source
SHIELD: Thwarting Code Authorship Attribution [PDF]
IEEE Transactions on Dependable and Secure Computing, 2023 Authorship attribution has become increasingly accurate, posing a serious privacy risk for programmers who wish to remain anonymous. In this article, we introduce SHIELD to examine the robustness of different code authorship attribution approaches ...
Mohammed Abuhamad +3 more
semanticscholar +1 more source
Digitális Bölcsészet, 2021 Petr Plecháč. Versification and Authorship Attribution. Prague: Institute of Czech Literature – Karolinum Press, 2021. ISBN 9788024648712. 98 oldal. https://doi.org/10.14712/9788024648903 Online verzió: https://versologie.cz/versification-authorship/
Levente Seláf
doaj +1 more source