Sara Narteni

Giacomo De Bernardi, Sara Narteni, Enrico Cambiaso et al.

Out-of-distribution detection is one of the most critical issue in the deployment of machine learning. The data analyst must assure that data in operation should be compliant with the training phase as well as understand if the environment has changed in a way that autonomous decisions would not be safe anymore. The method of the paper is based on eXplainable Artificial Intelligence (XAI); it takes into account different metrics to identify any resemblance between in-distribution and out of, as seen by the XAI model. The approach is non-parametric and distributional assumption free. The validation over complex scenarios (predictive maintenance, vehicle platooning, covert channels in cybersecurity) corroborates both precision in detection and evaluation of training-operation conditions proximity. Results are available via open source and open data at the following link: https://github.com/giacomo97cnr/Rule-based-ODD.

Sara Narteni, Alberto Carlevaro, Fabrizio Dabbene et al.

Everyday life is increasingly influenced by artificial intelligence, and there is no question that machine learning algorithms must be designed to be reliable and trustworthy for everyone. Specifically, computer scientists consider an artificial intelligence system safe and trustworthy if it fulfills five pillars: explainability, robustness, transparency, fairness, and privacy. In addition to these five, we propose a sixth fundamental aspect: conformity, that is, the probabilistic assurance that the system will behave as the machine learner expects. In this paper, we present a methodology to link conformal prediction with explainable machine learning by defining a new score function for rule-based classifiers that leverages rules predictive ability, the geometrical position of points within rules boundaries and the overlaps among rules as well, thanks to the definition of a geometrical rule similarity term. Furthermore, we address the problem of defining regions in the feature space where conformal guarantees are satisfied, by exploiting the definition of conformal critical set and showing how this set can be used to achieve new rules with improved performance on the target class. The overall methodology is tested with promising results on several datasets of real-world interest, such as domain name server tunneling detection or cardiovascular disease prediction.

Victor Toscano-Duran, Sara Narteni, Alberto Carlevaro et al.

The recent adoption of artificial intelligence in robotics has driven the development of algorithms that enable autonomous systems to adapt to complex social environments. In particular, safe and efficient social navigation is a key challenge, requiring AI not only to avoid collisions and deadlocks but also to interact intuitively and predictably with its surroundings. Methods based on probabilistic models and the generation of conformal safety regions have shown promising results in defining safety regions with a controlled margin of error, primarily relying on classification approaches and explicit rules to describe collision-free navigation conditions. This work extends the existing perspective by investigating how topological features can contribute to the creation of explainable safety regions in social navigation scenarios, enabling the classification and characterization of different simulation behaviors. Rather than relying on behaviors parameters to generate safety regions, we leverage topological features through topological data analysis. We first utilize global rule-based classification to provide interpretable characterizations of different simulation behaviors, distinguishing between safe and unsafe scenarios based on topological properties. Next, we define safety regions, $S_\varepsilon$, representing zones in the topological feature space where collisions are avoided with a maximum classification error of $\varepsilon$. These regions are constructed using adjustable SVM classifiers and order statistics, ensuring a robust and scalable decision boundary. Our approach initially separates simulations with and without collisions, outperforming methods that not incorporate topological features. We further refine safety regions to ensure deadlock-free simulations and integrate both aspects to define a compliant simulation space that guarantees safe and efficient navigation.

Javier Perera-Lago, Víctor Toscano-Durán, Eduardo Paluzo-Hidalgo et al.

Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture. In this domain, the imperative role of representative datasets is a cornerstone in shaping the trajectory of artificial intelligence (AI) development. Representative datasets are needed to train machine learning components properly. Proper training has multiple impacts: it reduces the final model's complexity, power, and uncertainties. In this paper, we investigate the reliability of the $\varepsilon$-representativeness method to assess the dataset similarity from a theoretical perspective for decision trees. We decided to focus on the family of decision trees because it includes a wide variety of models known to be explainable. Thus, in this paper, we provide a result guaranteeing that if two datasets are related by $\varepsilon$-representativeness, i.e., both of them have points closer than $\varepsilon$, then the predictions by the classic decision tree are similar. Experimentally, we have also tested that $\varepsilon$-representativeness presents a significant correlation with the ordering of the feature importance. Moreover, we extend the results experimentally in the context of unseen vehicle collision data for XGboost, a machine-learning component widely adopted for dealing with tabular data.