Related papers: Style Pooling: Automatic Text Style Obfuscation fo…

Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the…

Supervised learning models have been increasingly used for making decisions about individuals in applications such as hiring, lending, and college admission. These models may inherit pre-existing biases from training datasets and…

Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO). Given an artifact, especially a text t in question, an AA solution aims to…

Large language models (LLMs) often exhibit tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. While crucial for improvement, identifying the factors driving these…

This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition…

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases…

Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models. Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined characteristics to members of certain groups and…

Authorship attribution techniques are increasingly being used in online contexts such as sock puppet detection, malicious account linking, and cross-platform account linking. Yet, it is unknown whether these models perform equitably across…

Machine learning models can perpetuate unintended biases from unfair and imbalanced datasets. Evaluating and debiasing these datasets and models is especially hard in text datasets where sensitive attributes such as race, gender, and sexual…

Machine learning systems are increasingly deployed in high-stakes domains, yet they remain vulnerable to bias systematic disparities that disproportionately impact specific demographic groups. Traditional bias detection methods often depend…

Quantifying systematic disparities in numerical quantities such as employment rates and wages between population subgroups provides compelling evidence for the existence of societal biases. However, biases in the text written for members of…

While decision makers have begun to employ machine learning, machine learning models may make predictions that bias against certain demographic groups. Semi-automated bias detection tools often present reports of automatically-detected…

Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Dataset obfuscation refers to techniques in which random noise is added to the entries of a given dataset, prior to its public release, to protect against leakage of private information. In this work, dataset obfuscation under two…

Stylistic analysis of text is a key task in research areas ranging from authorship attribution to forensic analysis and personality profiling. The existing approaches for stylistic analysis are plagued by issues like topic influence, lack…

Recent advances in natural language processing have enabled powerful privacy-invasive authorship attribution. To counter authorship attribution, researchers have proposed a variety of rule-based and learning-based text obfuscation…