Andrea Bondavalli - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Andrea Bondavalli

Also published under: A. Bondavalli

Publications
151
Citations
1,437
Publications by Year
19882024
Co-Authors:
Show All Co-Authors (156)
Image of author Andrea Bondavalli

Andrea Bondavalli

Also published under: A. Bondavalli

Affiliation

Dept. of Mathematics and Informatics
University of Florence
Florence, Italy

Publication Topics

Biography

Andrea Bondavalli is a professor of computer science at the University of Firenze. Previously, he was a researcher in the Italian National Research Council, working at the CNUCE Institute in Pisa. His research activity is focused on dependability. In particular, he has been working on software fault tolerance, evaluation of dependability attributes such as reliability, availability, and performability, and on the development of design methodologies for real-time dependable systems. Dr. Bondavalli participated in several Projects funded by the European Community including ESPRIT BRA 3092 PDCS, 6362 PDCS-2, ESPRIT 27439 HIDE, and ESPRIT 20716 GUARDS and has authored or coauthored more than 80 papers, which have appeared in international journ...
Publications
151
Citations
1,437
Publications by Year
19882024
Co-Authors:
Show All Co-Authors (156)
Author's Published Works

Showing 1-25 of 151 results

  • Sort

Filter Results

Show

Sort By

Results

Fail-Controlled Classifiers: Do they Know when they don’t Know?

Tommaso Zoppi;Fahad Ahmed Khokhar;Andrea Ceccarelli;Leonardo Montecchi;Andrea Bondavalli

2024 IEEE 29th Pacific Rim International Symposium on Dependable Computing (PRDC)
Year: 2024 | Conference Paper |
Domain experts are desperately looking to solve decision-making problems by designing and training Machine Learning algorithms that can perform classification with the highest possible accuracy. No matter how hard they try, classifiers will always be prone to misclassifications due to a variety of reasons that make the decision boundary unclear. This complicates the integration of classifiers into...Show More

Fail-Controlled Classifiers: Do they Know when they don’t Know?

Tommaso Zoppi;Fahad Ahmed Khokhar;Andrea Ceccarelli;Leonardo Montecchi;Andrea Bondavalli

Year: 2024 | Conference Paper |

Improving the Efficiency of Software-Based Fault Protection Mechanisms With HUSTLE

Nicola Ferrante;Luca Fanucci;Francesco Rossi;Francesco Terrosi;Andrea Bondavalli

IEEE Access
Year: 2024 | Volume: 12 | Journal Article |
To achieve confidence in safety-critical systems, requires among others to meet high requirements on online testing of computer systems, as dictated by safety standards such as ISO26262, IEC61508, and CENELEC EN 5012X. Online testing can be performed through the periodic execution of online SW Test Libraries, which are widely used in safety-related applications as a valuable safety mechanism to pr...Show More

Improving the Efficiency of Software-Based Fault Protection Mechanisms With HUSTLE

Nicola Ferrante;Luca Fanucci;Francesco Rossi;Francesco Terrosi;Andrea Bondavalli

Year: 2024 | Volume: 12 | Journal Article |

Towards Trustworthy Autonomous Systems: Taxonomies and Future Perspectives

Francesco Flammini;Cristina Alcaraz;Emanuele Bellini;Stefano Marrone;Javier Lopez;Andrea Bondavalli

IEEE Transactions on Emerging Topics in Computing
Year: 2024 | Volume: 12, Issue: 2 | Journal Article |
Cited by: Papers (11)
The class of Trustworthy Autonomous Systems (TAS) includes cyber-physical systems leveraging on self-x technologies that make them capable to learn, adapt to changes, and reason under uncertainties in possibly critical applications and evolving environments. In the last decade, there has been a growing interest in enabling artificial intelligence technologies, such as advanced machine learning, ne...Show More

Towards Trustworthy Autonomous Systems: Taxonomies and Future Perspectives

Francesco Flammini;Cristina Alcaraz;Emanuele Bellini;Stefano Marrone;Javier Lopez;Andrea Bondavalli

Year: 2024 | Volume: 12, Issue: 2 | Journal Article |

Anomaly Detectors for Self-Aware Edge and IoT Devices

Tommaso Zoppi;Giovanni Merlino;Andrea Ceccarelli;Antonio Puliafito;Andrea Bondavalli

2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS)
Year: 2023 | Conference Paper |
Cited by: Papers (3)
With the growing processing power of computing systems and the increasing availability of massive datasets, machine learning algorithms have led to major breakthroughs in many different areas. This applies also to resource-constrained IoT and edge devices, which will often benefit from relatively small – but smart – local anomaly detection tasks that aim at protecting the device, or the informatio...Show More

Anomaly Detectors for Self-Aware Edge and IoT Devices

Tommaso Zoppi;Giovanni Merlino;Andrea Ceccarelli;Antonio Puliafito;Andrea Bondavalli

Year: 2023 | Conference Paper |

Modeling of GPGPU architectures for performance analysis of CUDA programs

Francesco Terrosi;Francesco Mariotti;Paolo Lollini;Andrea Bondavalli

2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS)
Year: 2023 | Conference Paper |
Graphics Processing Units (GPUs), originally developed for computer graphics, are now commonly used to accelerate parallel applications. Given that GPUs are designed to be as efficient as possible, evaluating their performance is crucial. This problem has been tackled in the last years by researchers that started to propose solutions such as analytical models and digital simulators, which are, how...Show More

Modeling of GPGPU architectures for performance analysis of CUDA programs

Francesco Terrosi;Francesco Mariotti;Paolo Lollini;Andrea Bondavalli

Year: 2023 | Conference Paper |

Toward Conceptual Analysis of Cyber-Physical Systems Projects Focusing on the Composition of Legacy Systems

André A. S. Ivo;Sheila Granato Ribeiro;Fátima Mattiello-Francisco;Andrea Bondavalli

IEEE Access
Year: 2023 | Volume: 11 | Journal Article |
Cited by: Papers (1)
The increase in connectivity and the continued need to evolve existing systems impose on system engineers the reality of dealing with System of Systems (SoS) concept in practice. The composition of legacy systems presents significant challenges, especially when a Cyber-Physical System (CPS) is involved. Due to the complexity of the interactions between CPS computational solutions and the physical ...Show More

Toward Conceptual Analysis of Cyber-Physical Systems Projects Focusing on the Composition of Legacy Systems

André A. S. Ivo;Sheila Granato Ribeiro;Fátima Mattiello-Francisco;Andrea Bondavalli

Year: 2023 | Volume: 11 | Journal Article |

Tolerate Failures of the Visual Camera With Robust Image Classifiers

Muhammad Atif;Andrea Ceccarelli;Tommaso Zoppi;Andrea Bondavalli

IEEE Access
Year: 2023 | Volume: 11 | Journal Article |
Cited by: Papers (2)
Deep Neural Networks (DNNs) have become an enabling technology for building accurate image classifiers, and are increasingly being applied in many ICT systems such as autonomous vehicles. Unfortunately, classifiers can be deceived by images that are altered due to failures of the visual camera, preventing the proper execution of the classification process. Therefore, it is of utmost importance to ...Show More

Tolerate Failures of the Visual Camera With Robust Image Classifiers

Muhammad Atif;Andrea Ceccarelli;Tommaso Zoppi;Andrea Bondavalli

Year: 2023 | Volume: 11 | Journal Article |

Robust Traffic Sign Recognition Against Camera Failures

Muhammad Atif;Andrea Ceccarelli;Tommaso Zoppi;Mohamad Gharib;Andrea Bondavalli

IEEE Open Journal of Intelligent Transportation Systems
Year: 2022 | Volume: 3 | Journal Article |
Cited by: Papers (11)
Failures of the vehicle camera may compromise the correct acquisition of frames, that are subsequently used by autonomous driving tasks. A clear understanding of the behavior of the autonomous driving tasks under such failure conditions, together with strategies to avoid safety is jeopardized, are indeed necessary. This study analyses and improve the performance of Traffic Sign Recognition (TSR) s...Show More

Robust Traffic Sign Recognition Against Camera Failures

Muhammad Atif;Andrea Ceccarelli;Tommaso Zoppi;Mohamad Gharib;Andrea Bondavalli

Year: 2022 | Volume: 3 | Journal Article |

Failure modes and failure mitigation in GPGPUs: a reference model and its application

Francesco Terrosi;Andrea Ceccarelli;Andrea Bondavalli

2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)
Year: 2022 | Conference Paper |
General Purpose GPUs (GPGPUs) are highly susceptible to both transient and permanent faults. This is a serious concern for their safe and reliable usage in many domains, from autonomous driving to High Performance Computing. The research and industrial community responded fiercely to this issue, by analyzing failures impact and devising failure mitigation strategies. This led to the definition of ...Show More

Failure modes and failure mitigation in GPGPUs: a reference model and its application

Francesco Terrosi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2022 | Conference Paper |

On the Properness of Incorporating Binary Classification Machine Learning Algorithms Into Safety-Critical Systems

Mohamad Gharib;Tommaso Zoppi;Andrea Bondavalli

IEEE Transactions on Emerging Topics in Computing
Year: 2022 | Volume: 10, Issue: 4 | Journal Article |
Cited by: Papers (6)
Manufacturers are willing to incorporate Machine Learning (ML) algorithms into their systems, especially those considered as Safety-Critical Systems (SCS). ML algorithms that perform binary classification (i.e., Binary Classifiers (BCs)) find a wide applicability as error, intrusion or failure detectors, provided that their performance complies with SCS safety requirements. However, the performanc...Show More

On the Properness of Incorporating Binary Classification Machine Learning Algorithms Into Safety-Critical Systems

Mohamad Gharib;Tommaso Zoppi;Andrea Bondavalli

Year: 2022 | Volume: 10, Issue: 4 | Journal Article |

Stochastic Activity Networks Templates: Supporting Variability in Performability Models

Leonardo Montecchi;Paolo Lollini;Andrea Bondavalli

IEEE Transactions on Reliability
Year: 2022 | Volume: 71, Issue: 2 | Journal Article |
Cited by: Papers (1)
Model-based evaluation is extensively used to estimate the performance and reliability of dependable systems. Traditionally, these systems were small and self-contained, and the main challenge for model-based evaluation has been the efficiency of the solution process. Recently, the problem of specifying and maintaining complex models has increasingly gained attention, as modern systems are charact...Show More

Stochastic Activity Networks Templates: Supporting Variability in Performability Models

Leonardo Montecchi;Paolo Lollini;Andrea Bondavalli

Year: 2022 | Volume: 71, Issue: 2 | Journal Article |

Feature Rankers to Predict Classification Performance of Unsupervised Intrusion Detectors

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

2021 10th Latin-American Symposium on Dependable Computing (LADC)
Year: 2021 | Conference Paper |
An anomaly-based Intrusion Detection System (IDS) consists of a monitor and a binary classifier, in which monitored system indicators are fed into a Machine Learning (ML) algorithm that detects anomalies due to attacks. Building such an IDS for a target system requires first to define a strategy to monitor features, then to select and evaluate many ML algorithms to find the most suitable candidate...Show More

Feature Rankers to Predict Classification Performance of Unsupervised Intrusion Detectors

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2021 | Conference Paper |

Detecting Intrusions by Voting Diverse Machine Learners: Is It Really Worth?

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

2021 IEEE 26th Pacific Rim International Symposium on Dependable Computing (PRDC)
Year: 2021 | Conference Paper |
Cited by: Papers (1)
Recent years have seen an astounding growth in the adoption of Machine Learning algorithms to classify data gathered through monitoring activities. Those algorithms can effectively classify data as system indicators, network packets, and logs according to a model they infer during training. This way, they provide sophisticated means to conduct intrusion detection by suspecting anomalies due to att...Show More

Detecting Intrusions by Voting Diverse Machine Learners: Is It Really Worth?

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2021 | Conference Paper |

Unsupervised Algorithms to Detect Zero-Day Attacks: Strategy and Application

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

IEEE Access
Year: 2021 | Volume: 9 | Journal Article |
Cited by: Papers (45)
In the last decade, researchers, practitioners and companies struggled for devising mechanisms to detect cyber-security threats. Among others, those efforts originated rule-based, signature-based or supervised Machine Learning (ML) algorithms that were proven effective for detecting those intrusions that have already been encountered and characterized. Instead, new unknown threats, often referred ...Show More

Unsupervised Algorithms to Detect Zero-Day Attacks: Strategy and Application

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2021 | Volume: 9 | Journal Article |

MADneSs: A Multi-Layer Anomaly Detection Framework for Complex Dynamic Systems

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

IEEE Transactions on Dependable and Secure Computing
Year: 2021 | Volume: 18, Issue: 2 | Journal Article |
Cited by: Papers (26)
Anomaly detection can infer the presence of errors without observing the target services, but detecting variations in the observable parts of the system on which the services reside. This is a promising technique in complex software-intensive systems, because either instrumenting the services' internals is exceedingly time-consuming, or encapsulation makes them not accessible. Unfortunately, in su...Show More

MADneSs: A Multi-Layer Anomaly Detection Framework for Complex Dynamic Systems

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2021 | Volume: 18, Issue: 2 | Journal Article |

Classification of Ethereum Vulnerabilities and their Propagations

Mirko Staderini;Caterina Palli;Andrea Bondavalli

2020 Second International Conference on Blockchain Computing and Applications (BCCA)
Year: 2020 | Conference Paper |
Cited by: Papers (12)
Blockchain technology is having an ever-increasing impact on distributed applications domain, since the adoption of Blockchain 2.0 led to the spread of smart contracts. In such a context, Ethereum is the framework with the highest diffusion in terms of smart contract's development, with a consequent rise of exploitation of code vulnerabilities, some of which causing bad financial losses. For this ...Show More

Classification of Ethereum Vulnerabilities and their Propagations

Mirko Staderini;Caterina Palli;Andrea Bondavalli

Year: 2020 | Conference Paper |

Into the Unknown: Unsupervised Machine Learning Algorithms for Anomaly-Based Intrusion Detection

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

2020 50th Annual IEEE-IFIP International Conference on Dependable Systems and Networks-Supplemental Volume (DSN-S)
Year: 2020 | Conference Paper |
Cited by: Papers (9)
Anomaly detection aims at identifying patterns in data that do not conform to the expected behavior, relying on machine-learning algorithms that are suited for binary classification. It has been arising as one of the most promising techniques to suspect intrusions, zero-day attacks and, under certain conditions, failures. This tutorial aims to instruct the attendees to the principles, application ...Show More

Into the Unknown: Unsupervised Machine Learning Algorithms for Anomaly-Based Intrusion Detection

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2020 | Conference Paper |

Governance & Autonomy: Towards a Governance-based Analysis of Autonomy in Cyber-Physical Systems-of-Systems

Mohamad Gharib;Paolo Lollini;Andrea Ceccarelli;Andrea Bondavalli

2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)
Year: 2020 | Conference Paper |
Cited by: Papers (2)
One of the main challenges in integrating CyberPhysical System-of-Systems (CPSoS) to function as a single unified system is the autonomy of its Cyber-Physical Systems (CPSs), which may lead to lack of coordination among CPSs and results in various kinds of conflicts. We advocate that to efficiently integrate CPSs within the CPSoS, we may need to adjust the autonomy of some CPSs in a way that allow...Show More

Governance & Autonomy: Towards a Governance-based Analysis of Autonomy in Cyber-Physical Systems-of-Systems

Mohamad Gharib;Paolo Lollini;Andrea Ceccarelli;Andrea Bondavalli

Year: 2020 | Conference Paper |

A Template-Based Methodology for the Specification and Automated Composition of Performability Models

Leonardo Montecchi;Paolo Lollini;Andrea Bondavalli

IEEE Transactions on Reliability
Year: 2020 | Volume: 69, Issue: 1 | Journal Article |
Cited by: Papers (10)
Dependability and performance analysis of modern systems is facing great challenges: their scale is growing, they are becoming massively distributed, interconnected, and evolving. Such complexity makes model-based assessment a difficult and time-consuming task. For the evaluation of large systems, reusable submodels are typically adopted as an effective way to address the complexity and to improve...Show More

A Template-Based Methodology for the Specification and Automated Composition of Performability Models

Leonardo Montecchi;Paolo Lollini;Andrea Bondavalli

Year: 2020 | Volume: 69, Issue: 1 | Journal Article |

Performability Analysis of a Tramway System with Virtual Tags and Local Positioning

Leandro Dias da Silva;Diamantea Mongelli;Paolo Lollini;Andrea Bondavalli;Gianluca Mandò

2019 9th Latin-American Symposium on Dependable Computing (LADC)
Year: 2019 | Conference Paper |
Cited by: Papers (2)
Current solutions for tramway Interlocking Systems are based on physical sensors (balizes) distributed along the infrastructure which detect passing of the trams and trigger different actions. This approach is not easily scalable and maintainable, and it is costly. The Regional Project SISTER aims at designing new architectural solutions for addressing the previous problems based on the virtualiza...Show More

Performability Analysis of a Tramway System with Virtual Tags and Local Positioning

Leandro Dias da Silva;Diamantea Mongelli;Paolo Lollini;Andrea Bondavalli;Gianluca Mandò

Year: 2019 | Conference Paper |

Practical Experience Report: Implementation, Verification and Validation of a Safe and Secure Communication Protocol for the Railway Domain

Duccio Bertieri;Tommaso Zoppi;Innocenzo Mungiello;Andrea Ceccarelli;Mario Barbareschi;Andrea Bondavalli

2019 9th Latin-American Symposium on Dependable Computing (LADC)
Year: 2019 | Conference Paper |
Cited by: Papers (2) | Patents (1)
Different communication protocols are currently being used for the railway domain. However, most of these protocols rely on many interlacing mechanisms and safety codes which raise their complexity. Therefore, companies operating in the railway domain, guided by the Italian railway network manager, devised the Protocollo Vitale Standard, a light network protocol that stems from the Euroradio and R...Show More

Practical Experience Report: Implementation, Verification and Validation of a Safe and Secure Communication Protocol for the Railway Domain

Duccio Bertieri;Tommaso Zoppi;Innocenzo Mungiello;Andrea Ceccarelli;Mario Barbareschi;Andrea Bondavalli

Year: 2019 | Conference Paper |

Evaluation of Anomaly Detection Algorithms Made Easy with RELOAD

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE)
Year: 2019 | Conference Paper |
Cited by: Papers (12)
Anomaly detection aims at identifying patterns in data that do not conform to the expected behavior. Despite anomaly detection has been arising as one of the most powerful techniques to suspect attacks or failures, dedicated support for the experimental evaluation is actually scarce. In fact, existing frameworks are mostly intended for the broad purposes of data mining and machine learning. Intuit...Show More

Evaluation of Anomaly Detection Algorithms Made Easy with RELOAD

Tommaso Zoppi;Andrea Ceccarelli;Andrea Bondavalli

Year: 2019 | Conference Paper |

On the Evaluation Measures for Machine Learning Algorithms for Safety-Critical Systems

Mohamad Gharib;Andrea Bondavalli

2019 15th European Dependable Computing Conference (EDCC)
Year: 2019 | Conference Paper |
Cited by: Papers (11)
The ability of Machine Learning (ML) algorithms to learn and work with incomplete knowledge has motivated many system manufacturers to include such algorithms in their products. However, some of these systems can be described as Safety-Critical Systems (SCS) since their failure may cause injury or even death to humans. Therefore, the performance of ML algorithms with respect to the safety requirem...Show More

On the Evaluation Measures for Machine Learning Algorithms for Safety-Critical Systems

Mohamad Gharib;Andrea Bondavalli

Year: 2019 | Conference Paper |

Toward a Model-Based Approach for Analyzing Information Quality Requirements for Smart Grid

Mohamad Gharib;Paolo Lollini;Andrea Bondavalli

2019 15th European Dependable Computing Conference (EDCC)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
Nowadays, most developed countries need to optimize their electricity production and consumption, which has led to the development of the Smart Grid (SG) concept. SG has a main objective of optimizing the generation, consumption, and management of electricity via information and communication technology. However, the vast amounts of information generated and processed in SG environments raise the ...Show More

Toward a Model-Based Approach for Analyzing Information Quality Requirements for Smart Grid

Mohamad Gharib;Paolo Lollini;Andrea Bondavalli

Year: 2019 | Conference Paper |

Resilient Access to Heterogeneous Measurement Data for Grid Observability

Nicola Nostro;Kamal Shahid;Andrea Bondavalli;Hans-Peter Schwefel

2019 15th European Dependable Computing Conference (EDCC)
Year: 2019 | Conference Paper |
Cited by: Papers (3)
The ability to fuse data from heterogeneous sources (such as Smart Meters etc.) in the low-voltage grid highly depends on the communication and data management infrastructure that allows an exchange of information between different grid assets. Failure or any attempt to attack this data fusion solution can lead to inefficient grid operation and in worst case even blackouts. Therefore, this paper d...Show More

Resilient Access to Heterogeneous Measurement Data for Grid Observability

Nicola Nostro;Kamal Shahid;Andrea Bondavalli;Hans-Peter Schwefel

Year: 2019 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.