8 August 2022 in IEEE Access
Machine learning (ML) algorithms are nowadays widely adopted in different contexts to perform autonomous decisions and predictions. Due to the high volume of data shared in the recent years, ML algorithms are more accurate and reliable since training and testing phases are more precise. An important concept to analyze when defining ML algorithms concerns adversarial machine learning attacks. These attacks aim to create manipulated datasets to mislead ML algorithm decisions. In this work, we propose new approaches able to detect and mitigate malicious adversarial machine learning attacks against a ML system. In particular, we investigate the Carlini-Wagner (CW), the fast gradient sign method (FGSM) and the Jacobian based saliency map (JSMA) attacks. The aim of this work is to exploit detection algorithms as countermeasures to these attacks. Initially, we performed some tests by using canonical ML algorithms with a hyperparameters optimization to improve metrics. Then, we adopt original reliable AI algorithms, either based on eXplainable AI (Logic Learning Machine) or Support Vector Data Description (SVDD). The obtained results show how the classical algorithms may fail to identify an adversarial attack, while the reliable AI methodologies are more prone to correctly detect a possible adversarial machine learning attack. The evaluation of the proposed methodology was carried out in terms of good balance between FPR and FNR on real world application datasets: Domain Name System (DNS) tunneling, Vehicle Platooning and Remaining Useful Life (RUL). In addition, a statistical analysis was performed to improve the robustness of the trained models, including evaluating their performance in terms of runtime and memory consumption.
17 November 2022 in PLOS ONE
Despite the growing availability of artificial intelligence models for predicting type 2 diabetes, there is still a lack of personalized approaches to quantify minimum viable changes in biomarkers that may help reduce the individual risk of developing disease. The aim of this article is to develop a new method, based on counterfactual explanations, to generate personalized recommendations to reduce the one-year risk of type 2 diabetes. Ten routinely collected biomarkers extracted from Electronic Medical Records of 2791 patients at low risk and 2791 patients at high risk of type 2 diabetes were analyzed. Two regions characterizing the two classes of patients were estimated using a Support Vector Data Description classifier. Counterfactual explanations (i.e., minimal changes in input features able to change the risk class) were generated for patients at high risk and evaluated using performance metrics (availability, validity, actionability, similarity, and discriminative power) and a qualitative survey administered to seven expert clinicians. Results showed that, on average, the requested minimum viable changes implied a significant reduction of fasting blood sugar, systolic blood pressure, and triglycerides and a significant increase of high-density lipoprotein in patients at risk of diabetes. A significant reduction in body mass index was also recommended in most of the patients at risk, except in females without hypertension. In general, greater changes were recommended in hypertensive patients compared to non-hypertensive ones. The experts were overall satisfied with the proposed approach although in some cases the proposed recommendations were deemed insufficient to reduce the risk in a clinically meaningful way. Future research will focus on a larger set of biomarkers and different comorbidities, also incorporating clinical guidelines whenever possible. Development of additional mathematical and clinical validation approaches will also be of paramount importance.
29 October 2021 in IEEE Intelligent Systems
Safety engineering and Artificial Intelligence (AI) are two fields which still need investigation on their reciprocal interactions. Safety should be guaranteed when autonomous decision may lead to risk for the environment and the human. The present work addresses how Support Vector Data Description (SVDD) can be re-designed to detect safety regions in a cyber physical system with zero statistical error. Rule-based knowledge extraction is also presented, to let the SVDD be understandable. Two applications are considered for performance evaluation: DNS Tunneling detection and Region of Attraction (ROA) estimation of dynamic systems.Results demonstrate how the new SVDD and its intelligible representation are both suitable in designing safety regions, still maximizing the space of the working conditions.
3 June 2022 in IEEE Access
Increasingly in recent times, the mere prediction of a machine learning algorithm is considered insufficient to gain complete control over the event being predicted. A machine learning algorithm should be considered reliable in the way it allows to extract more knowledge and information than just having a prediction at hand. In this perspective, the counterfactual theory plays a central role. By definition, a counterfactual is the smallest variation of the input such that it changes the predicted behaviour. The paper addresses counterfactuals through Support Vector Data Description (SVDD), empowered by explainability and metric for assessing the counterfactual quality. After showing the specific case in which an analytical solution may be found (under Euclidean distance and linear kernel), an optimisation problem is posed for any type of distances and kernels. The vehicle platooning application is the use case considered to demonstrate how the outlined methodology may offer support to safety-critical applications as well as how explanation may shed new light into the control of the system at hand.
6 September 2023 in Computers and Electronics in Agriculture
27 November 2023 in IEEE Transactions on Artificial Intelligence
Explainability has become crucial in Artificial Intelligence studies and, as the complexity of the model increases, so does the complexity of its explanation. However, the higher the complexity of the problem, the higher the amount of information it may provide, and this information can be exploited to generate a more precise explanation of how the model works. One of the most valuable ways to recover such input-output relation is to extract counterfactual explanations that allow us to find minimal changes from an observation to another one belonging to a different class. In this article, we propose a novel methodology to extract multiple counterfactual explanations (MUCH, MUlti Counterfactual via Halton sampling) from an original Multi-Class Support Vector Data Description algorithm. To evaluate the performance of the proposed method, we extracted a set of counterfactual explanations from three state-of-the-art datasets achieving satisfactory results that pave the way to a range of real-world applications.