Related papers: What's Pulling the Strings? Evaluating Integrity a…

Including children's images in datasets has raised ethical concerns, particularly regarding privacy, consent, data protection, and accountability. These datasets, often built by scraping publicly available images from the Internet, can…

Ensuring responsible use of artificial intelligence (AI) has become imperative as autonomous systems increasingly influence critical societal domains. However, the concept of trustworthy AI remains broad and multi-faceted. This thesis…

Generative AI and Large Language Models (LLMs) hold promise for automating spreadsheet formula creation. However, due to hallucinations, bias and variable user skill, outputs obtained from generative AI cannot be assumed to be accurate or…

Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates…

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…

As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…

This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…

Fairness and accountability are two essential pillars for trustworthy Artificial Intelligence (AI) in healthcare. However, the existing AI model may be biased in its decision marking. To tackle this issue, we propose an adversarial…

This paper examines two prominent formal trade-offs in artificial intelligence (AI) -- between predictive accuracy and fairness, and between predictive accuracy and interpretability. These trade-offs have become a central focus in normative…

The increasing use of generative AI for resume screening is predicated on the assumption that it offers an unbiased alternative to biased human decision-making. However, this belief fails to address a critical question: are these AI systems…

Many recent neural models have shown remarkable empirical results in Machine Reading Comprehension, but evidence suggests sometimes the models take advantage of dataset biases to predict and fail to generalize on out-of-sample data. While…

The proliferation of generative AI and deceptive synthetic media threatens the global information ecosystem, especially across the Global Majority. This report from WITNESS highlights the limitations of current AI detection tools, which…

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

Generative Artificial Intelligence (GenAI) is now widespread in education, yet the efficacy of GenAI systems remains constrained by the quality and interpretation of the labeled data used to train and evaluate them. Studies commonly report…

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…

Due to significant improvements in performance in recent years, neural networks are currently used for an ever-increasing number of applications. However, neural networks have the drawback that their decisions are not readily interpretable…

To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide…

ConceptLens is an innovative tool designed to illuminate the intricate workings of deep neural networks (DNNs) by visualizing hidden neuron activations. By integrating deep learning with symbolic methods, ConceptLens offers users a unique…

This study explores the integration of contextual explanations into AI-powered loan decision systems to enhance trust and usability. While traditional AI systems rely heavily on algorithmic transparency and technical accuracy, they often…