Autonomous vehicles security: Challenges and solutions using blockchain and artificial intelligence
The arrival of autonomous vehicles (AVs) promises many great benefits, including increased
safety and reduced energy consumption, pollution, and congestion. However, these engines …
safety and reduced energy consumption, pollution, and congestion. However, these engines …
Falsification detection system for IoV using randomized search optimization ensemble algorithm
Falsification detection is a critical advance in ensuring that real-time information about
vehicles and their movement states is certified on the Internet of Vehicles (IoV). Thus …
vehicles and their movement states is certified on the Internet of Vehicles (IoV). Thus …
Counterfactual building and evaluation via eXplainable support vector data description
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 …
considered insufficient to gain complete control over the event being predicted. A machine …
eXplainable and reliable against adversarial machine learning in data analytics
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 …
perform autonomous decisions and predictions. Due to the high volume of data shared in …
A new SVDD approach to reliable and explainable AI
A Carlevaro, M Mongelli - IEEE Intelligent Systems, 2021 - ieeexplore.ieee.org
Safety engineering and artificial intelligence are two fields that still need investigation on
their reciprocal interactions. Safety should be guaranteed when autonomous decision may …
their reciprocal interactions. Safety should be guaranteed when autonomous decision may …
Explainable AI for Cyber-Physical Systems: Issues and Challenges
Artificial intelligence and cyber-physical systems (CPS) are two of the key technologies of
the future that are enabling major global shifts. However, most of the current …
the future that are enabling major global shifts. However, most of the current …
On the Intersection of Explainable and Reliable AI for physical fatigue prediction
In the era of Industry 4.0, the use of Artificial Intelligence (AI) is widespread in occupational
settings. Since dealing with human safety, explainability and trustworthiness of AI are even …
settings. Since dealing with human safety, explainability and trustworthiness of AI are even …
Rule-based out-of-distribution detection
G De Bernardi, S Narteni, E Cambiaso… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
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 …
learning. The data analyst must assure that data in operation should be compliant with the …
Weighted mutual information for out-of-distribution detection
G De Bernardi, S Narteni, E Cambiaso… - World Conference on …, 2023 - Springer
Out-of-distribution detection has become an important theme in machine learning (ML) field,
since the recognition of unseen data either “similar” or not (in-or out-of-distribution) to the …
since the recognition of unseen data either “similar” or not (in-or out-of-distribution) to the …
A New XAI-based Evaluation of Generative Adversarial Networks for IMU Data Augmentation
Data augmentation is a widespread innovative technique in Artificial Intelligence: it aims at
creating new synthetic data given an existing real baseline, thus allowing to overcome the …
creating new synthetic data given an existing real baseline, thus allowing to overcome the …