The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.
Human mobility data play a crucial role in understanding mobility patterns and developing analytical services across various domains such as urban planning, transportation, and public health. However, due to the sensitive nature of this data, accurately identifying privacy risks is essential before deciding to release it to the public. Recent work has proposed the use of machine learning models for predicting privacy risk on raw mobility trajectories and the use of shap for risk explanation. However, applying shap to mobility data results in explanations that are of limited use both for privacy experts and end-users. In this work, we present a novel version of the Expert privacy risk prediction and explanation framework specifically tailored for human mobility data. We leverage state-of-the-art algorithms in time series classification, as Rocket and InceptionTime, to improve risk prediction while reducing computation time. Additionally, we address two key issues with shap explanation on mobility data: first, we devise an entropy-based mask to efficiently compute shap values for privacy risk in mobility data; second, we develop a module for interactive analysis and visualization of shap values over a map, empowering users with an intuitive understanding of shap values and privacy risk.
In recent years we are witnessing the diffusion of AI systems based on powerful Machine Learning models which find application in many critical contexts such as medicine and financial market. In such contexts, it is important to design Trustworthy AI systems while guaranteeing privacy protection. However, some attacks on the privacy of Machine Learning models have been designed to show the threats of exposing such models. Membership Inference is one of the simplest privacy threats faced by Machine Learning models. It is based on the assumption that an adversary, observing the confidence of the model prediction, can infer whether a particular record was used for training the classifier. A variant, called Label-Only attack, exploits the adversary’s knowledge of the training data statistics to infer the record membership without accessing the confidence score of the prediction. In this paper, we propose a variant of the Label-Only attack, called Aloa, which estimates the prediction confidence exploiting a mechanism that is completely agnostic to the input data distributions. In fact, it requires neither statistical knowledge of the data nor the type of variables. Experimental results show better performance of our attack with respect to the competitors.
Fairness in Machine Learning has become a concern, particularly if models are deployed in high-stakes decision-making. Most existing approaches aim to enforce fairness during training, but they face significant challenges for the scalability and the effectiveness of fairness enforcement. To address these limitations, we propose a method for training fair classifiers under multiple group and intersectional fairness constraints with high predictive performance. We combine an Augmented Lagrangian learning procedure with a tunable performance budget , which regulates the trade-off between fairness and utility. Experiments demonstrate that our method mitigates bias while scaling efficiently with increasing problem complexity. By adjusting the performance budget, we provide a flexible mechanism to balance fairness enforcement and predictive performance, offering a solution for real-world applications.