Related papers: Attribution for Enhanced Explanation with Transfer…

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable…

The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some…

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of inputs. Gradient integration is a building block in the…

With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual…

Machine Learning (ML) models are known to be vulnerable to adversarial inputs and researchers have demonstrated that even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible. These systems represent…

Adversarial examples have attracted widespread attention in security-critical applications because of their transferability across different models. Although many methods have been proposed to boost adversarial transferability, a gap still…

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable…

We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of…

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations…

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…

Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of…

Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be applied independently of how the models were trained.…

Multi-Agent Deep Reinforcement Learning (MADRL) was proven efficient in solving complex problems in robotics or games, yet most of the trained models are hard to interpret. While learning intrinsically interpretable models remains a…

The deployment of Machine Learning models intraoperatively for tissue characterisation can assist decision making and guide safe tumour resections. For image classification models, pixel attribution methods are popular to infer…

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…

Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…