Related papers: Red Teaming Deep Neural Networks with Feature Synt…

Deep neural networks (DNNs) have been shown to outperform traditional machine learning algorithms in a broad variety of application domains due to their effectiveness in modeling complex problems and handling high-dimensional datasets. Many…

Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models can match human accuracy on standard tasks, such parity does not guarantee that their…

Determining whether a configurable software system has a performance bug or it was misconfigured is often challenging. While there are numerous debugging techniques that can support developers in this task, there is limited empirical…

Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets…

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them…

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. Currently, there is no clear insight into how slight perturbations cause such a large difference in classification results and how we can design a more robust…

Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this…

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…

Recent research has developed a number of eXplainable AI (XAI) techniques, such as gradient-based approaches, input perturbation-base methods, and black-box explanation methods. While these XAI techniques can extract meaningful insights…

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…

With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for Explainable AI. Interpretability and explanation methods for gaining a better understanding about the problem…

As interpretability has been pointed out as the obstacle to the adoption of Deep Neural Networks (DNNs), there is an increasing interest in solving a transparency issue to guarantee the impressive performance. In this paper, we demonstrate…

The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train…

Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to…

EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target.…

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human…

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…

Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on inputs outside its training domain. For such out-of-distribution (OOD) inputs, the model can…

AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has…

We describe algorithms for symbolic reasoning about executable models of type systems, supporting three queries intended for designers of type systems. First, we check for type soundness bugs and synthesize a counterexample program if such…