Biblio

The range of text analysis methods in the field of natural language processing (NLP) has become more and more extensive thanks to the increasing computational resources of the 21st century. As a result, many deep learning-based solutions have been proposed for the purpose of authorship attribution, as they offer more flexibility and automated feature extraction compared to traditional statistical methods. A number of solutions have appeared for the attribution of English texts, however, the number of methods designed for Hungarian language is extremely small. Hungarian is a morphologically rich language, sentence formation is flexible and the alphabet is different from other languages. Furthermore, a language specific POS tagger, pretrained word embeddings, dependency parser, etc. are required. As a result, methods designed for other languages cannot be directly applied on Hungarian texts. In this paper, we review deep learning-based authorship attribution methods for English texts and offer techniques for the adaptation of these solutions to Hungarian language. As a part of the paper, we collected a new dataset consisting of Hungarian literary works of 15 authors. In addition, we extensively evaluate the implemented methods on the new dataset.

A text is a meaningful source of information. Capturing the right patterns in written text gives metrics to measure and infer to what extent this text belongs or is relevant to a specific author. This research aims to introduce a new feature that goes more in deep in the language structure. The feature introduced is based on an attempt to differentiate stylistic changes among authors according to the different sentence structure each author uses. The study showed the effect of introducing this new feature to machine learning models to enhance their performance. It was found that the prediction of authors was enhanced by adding sentence structure as an additional feature as the f1\_scores increased by 0.3% and when normalizing the data and adding the feature it increased by 5%.

Authorship attribution is the problem of identifying the author of texts based on the author's writing style. It is usually assumed that the writing style contains traits inaccessible to conscious manipulation and can thus be safely used to identify the author of a text. Several style markers have been proposed in the literature, nevertheless, there is still no consensus on which best represent the choices of authors. Here we assume an agnostic viewpoint on the dispute for the best set of features that represents an author's writing style. We rather investigate how different sources of information may unveil different aspects of an author's style, complementing each other to improve the overall process of authorship attribution. For this we model authorship attribution as a multi-view learning task. We assess the effectiveness of our proposal applying it to a set of well-studied corpora. We compare the performance of our proposal to the state-of-the-art approaches for authorship attribution. We thoroughly analyze how the multi-view approach improves on methods that use a single data source. We confirm that our approach improves both in accuracy and consistency of the methods and discuss how these improvements are beneficial for linguists and domain specialists.

Identification of source code authorship is vital for attribution. In this work, a machine learning framework is described to identify source code authorship. The framework integrates the features extracted using natural language processing based approaches and abstract syntax tree of the code. We evaluate the methodology on Google Code Jam dataset. We present the performance measures of the logistic regression and deep learning on the dataset.

Authorship attribution, an NLP problem where anonymous text is matched to its author, has important, cross-disciplinary applications, particularly those concerning cyber-defense. Our research examines the degree of sensitivity that attention-based models have to adversarial perturbations. We ask, what is the minimal amount of change necessary to maximally confuse a transformer model? In our investigation we examine a balanced subset of emails from the Enron email dataset, calculating the performance of our model before and after email signatures have been perturbed. Results show that the model's performance changed significantly in the absence of a signature, indicating the importance of email signatures in email authorship detection. Furthermore, we show that these models rely on signatures for shorter emails much more than for longer emails. We also indicate that additional research is necessary to investigate stylometric features and adversarial training to further improve classification model robustness.

Authorship Attribution (AA) is currently applied in several applications, among which fraud detection and anti-plagiarism checks: this task can leverage stylometry and Natural Language Processing techniques. In this work, we explored some strategies to enhance the performance of an AA task for the automatic detection of false and misleading information (e.g., fake news). We set up a text classification model for AA based on stylometry exploiting recurrent deep neural networks and implemented two learning tasks trained on the same collection of fake and real news, comparing their performances: one is based on Federated Learning architecture, the other on a centralized architecture. The goal was to discriminate potential fake information from true ones when the fake news comes from heterogeneous sources, with different styles. Preliminary experiments show that a distributed approach significantly improves recall with respect to the centralized model. As expected, precision was lower in the distributed model. This aspect, coupled with the statistical heterogeneity of data, represents some open issues that will be further investigated in future work.

Authorship attribution is the problem of studying an anonymous text and finding the corresponding author in a set of candidate authors. In this paper, we propose a method based on N-grams model for the problem of authorship attribution. Several measures are used to assign an anonymous text to an author. The different variants of the proposed method are implemented and validated on PAN benchmarks. The numerical results are encouraging and demonstrate the benefit of the proposed idea.

The proposed combination of statistical methods has proved efficient for authorship attribution. The complex analysis method based on the proposed combination of statistical methods has made it possible to minimize the number of phoneme groups by which the authorial differentiation of texts has been done.

Writing style is a combination of consistent decisions associated with a specific author at different levels of language production, including lexical, syntactic, and structural. In this paper, we introduce a style-aware neural model to encode document information from three stylistic levels and evaluate it in the domain of authorship attribution. First, we propose a simple way to jointly encode syntactic and lexical representations of sentences. Subsequently, we employ an attention-based hierarchical neural network to encode the syntactic and semantic structure of sentences in documents while rewarding the sentences which contribute more to capturing the writing style. Our experimental results, based on four benchmark datasets, reveal the benefits of encoding document information from all three stylistic levels when compared to the baseline methods in the literature.

A new program has been developed for style and authorship attribution. Differentiation of styles by transcription symbols has proved to be efficient The novel approach involves a combination of two ways of transforming texts into their transcription variants. The java programming language makes it possible to improve efficiency of style and authorship attribution.

In this paper, we explore the authorship attribution of The Golden Lotus using the traditional machine learning method of text classification. There are four candidate authors: Shizhen Wang, Wei Xu, Kaixian Li and Zhideng Wang. We choose The Golden Lotus's poems and four candidate authors' poems as data set. According to the characteristics of Chinese ancient poem, we choose Chinese character, rhyme, genre and overlapped word as features. We use six supervised machine learning algorithms, including Logistic Regression, Random Forests, Decision Tree and Naive Bayes, SVM and KNN classifiers respectively for text binary classification and multi-classification. According to two experiments results, the style of writing of Wei Xu's poems is the most similar to that of The Golden Lotus. It is proved that among four authors, Wei Xu most likely be the author of The Golden Lotus.

Open-source software is open to anyone by design, whether it is a community of developers, hackers or malicious users. Authors of open-source software typically hide their identity through nicknames and avatars. However, they have no protection against authorship attribution techniques that are able to create software author profiles just by analyzing software characteristics. In this paper we present an author imitation attack that allows to deceive current authorship attribution systems and mimic a coding style of a target developer. Withing this context we explore the potential of the existing attribution techniques to be deceived. Our results show that we are able to imitate the coding style of the developers based on the data collected from the popular source code repository, GitHub. To subvert author imitation attack, we propose a novel author obfuscation approach that allows us to hide the coding style of the author. Unlike existing obfuscation tools, this new obfuscation technique uses transformations that preserve code readability. We assess the effectiveness of our attacks on several datasets produced by actual developers from GitHub, and participants of the GoogleCodeJam competition. Throughout our experiments we show that the author hiding can be achieved by making sensible transformations which significantly reduce the likelihood of identifying the author's style to 0% by current authorship attribution systems.

At a time when all it takes to open a Twitter account is a mobile phone, the act of authenticating information encountered on social media becomes very complex, especially when we lack measures to verify digital identities in the first place. Because the platform supports anonymity, fake news generated by dubious sources have been observed to travel much faster and farther than real news. Hence, we need valid measures to identify authors of misinformation to avert these consequences. Researchers propose different authorship attribution techniques to approach this kind of problem. However, because tweets are made up of only 280 characters, finding a suitable authorship attribution technique is a challenge. This research aims to classify authors of tweets by comparing machine learning methods like logistic regression and naive Bayes. The processes of this application are fetching of tweets, pre-processing, feature extraction, and developing a machine learning model for classification. This paper illustrates the text classification for authorship process using machine learning techniques. In total, there were 46,895 tweets used as both training and testing data, and unique features specific to Twitter were extracted. Several steps were done in the pre-processing phase, including removal of short texts, removal of stop-words and punctuations, tokenizing and stemming of texts as well. This approach transforms the pre-processed data into a set of feature vector in Python. Logistic regression and naive Bayes algorithms were applied to the set of feature vectors for the training and testing of the classifier. The logistic regression based classifier gave the highest accuracy of 91.1% compared to the naive Bayes classifier with 89.8%.

Although Stylometry has been effectively used for Authorship Attribution, there is a growing number of methods being developed that allow authors to mask their identity [2, 13]. In this paper, we investigate the usage of non-traditional feature sets for Authorship Attribution. By using non-traditional feature sets, one may be able to reveal the identity of adversarial authors who are attempting to evade detection from Authorship Attribution systems that are based on more traditional feature sets. In addition, we demonstrate how GEFeS (Genetic & Evolutionary Feature Selection) can be used to evolve high-performance hybrid feature sets composed of two non-traditional feature sets for Authorship Attribution: LIWC (Linguistic Inquiry & Word Count) and Sentiment Analysis. These hybrids were able to reduce the Adversarial Effectiveness on a test set presented in [2] by approximately 33.4%.

This paper proposed method for source code authorship attribution using modern natural language processing methods. Our method based on text embedding with convolutional recurrent neural network reaches 94.5% accuracy within 500 authors in one dataset, which outperformed many state of the art models for authorship attribution. Our approach is dealing with source code as with natural language texts, so it is potentially programming language independent with more potential of future improving.

The use of typing biometrics—the characteristic typing patterns of individual keyboard users—has been studied extensively in the context of enhancing multi-factor authentication services. The key starting point for such work has been the collection of high-fidelity local timing data, and the key (implicit) security assumption has been that such biometrics could not be obtained by other means. We show that the latter assumption to be false, and that it is entirely feasible to obtain useful typing biometric signatures from third-party timing logs. Specifically, we show that the logs produced by realtime collaboration services during their normal operation are of sufficient fidelity to successfully impersonate a user using remote data only. Since the logs are routinely shared as a byproduct of the services' operation, this creates an entirely new avenue of attack that few users would be aware of. As a proof of concept, we construct successful biometric attacks using only the log-based structure (complete editing history) of a shared Google Docs, or Zoho Writer, document which is readily available to all contributing parties. Using the largest available public data set of typing biometrics, we are able to create successful forgeries 100% of the time against a commercial biometric service. Our results suggest that typing biometrics are not robust against practical forgeries, and should not be given the same weight as other authentication factors. Another important implication is that the routine collection of detailed timing logs by various online services also inherently (and implicitly) contains biometrics. This not only raises obvious privacy concerns, but may also undermine the effectiveness of network anonymization solutions, such as ToR, when used with existing services.

The veil of anonymity provided by smartphones with pre-paid SIM cards, public Wi-Fi hotspots, and distributed networks like Tor has drastically complicated the task of identifying users of social media during forensic investigations. In some cases, the text of a single posted message will be the only clue to an author's identity. How can we accurately predict who that author might be when the message may never exceed 140 characters on a service like Twitter? For the past 50 years, linguists, computer scientists, and scholars of the humanities have been jointly developing automated methods to identify authors based on the style of their writing. All authors possess peculiarities of habit that influence the form and content of their written works. These characteristics can often be quantified and measured using machine learning algorithms. In this paper, we provide a comprehensive review of the methods of authorship attribution that can be applied to the problem of social media forensics. Furthermore, we examine emerging supervised learning-based methods that are effective for small sample sizes, and provide step-by-step explanations for several scalable approaches as instructional case studies for newcomers to the field. We argue that there is a significant need in forensics for new authorship attribution algorithms that can exploit context, can process multi-modal data, and are tolerant to incomplete knowledge of the space of all possible authors at training time.

Different data mining techniques are employed in stylometry domain for performing authorship attribution tasks. Sometimes to improve the decision system the discretization of input data can be applied. In many cases such approach allows to obtain better classification results. On the other hand, there were situations in which discretization decreased overall performance of the system. Therefore, the question arose what would be the result if only some selected attributes were discretized. The paper presents the results of the research performed for forward sequential selection of attributes to be discretized. The influence of such approach on the performance of the decision system, based on Naive Bayes classifier in authorship attribution domain, is presented. Some basic discretization methods and different approaches to discretization of the test datasets are taken into consideration.

Internet security issues require authorship identification for all kinds of internet contents; however, authorship identification for microblog users is much harder than other documents because microblog texts are too short. Moreover, when the number of candidates becomes large, i.e., big data, it will take long time to identify. Our proposed method solves these problems. The experimental results show that our method successfully identifies the authorship with 53.2% of precision out of 10,000 microblog users in the almost half execution time of previous method.
 

By representing large corpora with concise and meaningful elements, topic-based generative models aim to reduce the dimension and understand the content of documents. Those techniques originally analyze on words in the documents, but their extensions currently accommodate meta-data such as authorship information, which has been proved useful for textual modeling. The importance of learning authorship is to extract author interests and assign authors to anonymous texts. Author-Topic (AT) model, an unsupervised learning technique, successfully exploits authorship information to model both documents and author interests using topic representations. However, the AT model simplifies that each author has equal contribution on multiple-author documents. To overcome this limitation, we assumes that authors give different degrees of contributions on a document by using a Dirichlet distribution. This automatically transforms the unsupervised AT model to Supervised Author-Topic (SAT) model, which brings a novelty of authorship prediction on anonymous texts. The SAT model outperforms the AT model for identifying authors of documents written by either single authors or multiple authors with a better Receiver Operating Characteristic (ROC) curve and a significantly higher Area Under Curve (AUC). The SAT model not only achieves competitive performance to state-of-the-art techniques e.g. Random forests but also maintains the characteristics of the unsupervised models for information discovery i.e. Word distributions of topics, author interests, and author contributions.
 

Source code authorship attribution is the task of determining the author of source code whose author is not explicitly known. One specific method of source code authorship attribution that has been shown to be extremely effective is the SCAP method. This method, however, relies on a parameter L that has heretofore been quite nebulous. In the SCAP method, each candidate author's known work is represented as a profile of that author, where the parameter L defines the profile's maximum length. In this study, alternative approaches for selecting a value for L were investigated. Several alternative approaches were found to perform better than the baseline approach used in the SCAP method. The approach that performed the best was empirically shown to improve the performance from 91.0% to 97.2% measured as a percentage of documents correctly attributed using a data set consisting of 7,231 programs written in Java and C++.