1 code implementation • 29 Apr 2024 • Ruben Grewal, Paolo Tonella, Andrea Stocco
The automated real-time recognition of unexpected situations plays a crucial role in the safety of autonomous vehicles, especially in unsupported and unpredictable scenarios.
no code implementations • 20 Mar 2024 • Luca Giamattei, Matteo Biagiola, Roberto Pietrantuono, Stefano Russo, Paolo Tonella
Our extension aims at eliminating some of the possible reasons for the poor performance of RL observed in our replication: (1) the presence of reward components providing contrasting or useless feedback to the RL agent; (2) the usage of an RL algorithm (Q-learning) which requires discretization of an intrinsically continuous state space.
no code implementations • 20 Jul 2023 • Matteo Biagiola, Paolo Tonella
State-of-the-art ADS testing approaches modify the controllable attributes of a simulated driving environment until the ADS misbehaves.
1 code implementation • 22 May 2023 • Matteo Biagiola, Paolo Tonella
The failure prediction acts as a fitness function, guiding the generation towards failure environment configurations, while saving computation time by deferring the execution of the DRL agent in the environment to those configurations that are more likely to expose failures.
1 code implementation • 14 May 2023 • Matteo Biagiola, Andrea Stocco, Vincenzo Riccio, Paolo Tonella
Our empirical evaluation shows that the ensemble failure predictor by the digital siblings is superior to each individual simulator at predicting the failures of the digital twin.
1 code implementation • 5 Apr 2023 • Michael Weiss, Paolo Tonella
Systems relying on large-scale DNNs thus have to call the corresponding model over the network, leading to substantial costs for hosting and running the large-scale remote model, costs which are often charged on a per-use basis.
1 code implementation • 21 Dec 2022 • Vincenzo Riccio, Paolo Tonella
In this paper, we investigate to what extent TIGs can generate valid inputs, according to both automated and human validators.
no code implementations • 14 Dec 2022 • Michael Weiss, Paolo Tonella
After overviewing the main approaches to uncertainty estimation and discussing their pros and cons, we motivate the need for a specific empirical assessment method that can deal with the experimental setting in which supervisors are used, where the accuracy of the DNN matters only as long as the supervisor lets the DLS continue to operate.
no code implementations • 21 Jul 2022 • Michael Weiss, André García Gómez, Paolo Tonella
In this paper, we propose a novel way to generate ambiguous inputs to test DNN supervisors and used it to empirically compare several existing supervisor techniques.
3 code implementations • 2 May 2022 • Michael Weiss, Paolo Tonella
Test Input Prioritizers (TIP) for Deep Neural Networks (DNN) are an important technique to handle the typically very large test datasets efficiently, saving computation and labeling costs.
1 code implementation • 21 Dec 2021 • Andrea Stocco, Brian Pulfer, Paolo Tonella
In this paper, we shed light on the problem of generalizing testing results obtained in a driving simulator to a physical platform and provide a characterization and quantification of the sim2real gap affecting SDC testing.
1 code implementation • 15 Sep 2021 • Vincenzo Riccio, Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella
The adequacy of the test data used to test such systems can be assessed by their ability to expose artificially injected faults (mutations) that simulate real DL faults.
1 code implementation • 5 Jul 2021 • Tahereh Zohdinasab, Vincenzo Riccio, Alessio Gambi, Paolo Tonella
Deep Learning (DL) has been successfully applied to a wide range of application domains, including safety-critical ones.
2 code implementations • 10 Mar 2021 • Michael Weiss, Rwiddhi Chakraborty, Paolo Tonella
As an adequacy criterion, it has been used to assess the strength of DL test suites.
1 code implementation • 4 Mar 2021 • Valerio Terragni, Gunel Jahangirova, Paolo Tonella, Mauro Pezzè
This demo presents the implementation and usage details of GASSERT, the first tool to automatically improve assertion oracles.
Software Engineering
2 code implementations • 1 Feb 2021 • Michael Weiss, Paolo Tonella
Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals.
1 code implementation • 7 Jan 2021 • Andrea Romdhana, Alessio Merlo, Mariano Ceccato, Paolo Tonella
We have developed ARES, a Deep RL approach for black-box testing of Android apps.
Software Engineering
1 code implementation • 29 Dec 2020 • Michael Weiss, Paolo Tonella
Uncertainty and confidence have been shown to be useful metrics in a wide variety of techniques proposed for deep learning testing, including test data selection and system supervision. We present uncertainty-wizard, a tool that allows to quantify such uncertainty and confidence in artificial neural networks.
1 code implementation • 6 Jul 2020 • Vincenzo Riccio, Paolo Tonella
If the frontier of misbehaviours is outside the validity domain of the system, the quality check is passed.
2 code implementations • 24 Oct 2019 • Nargiz Humbatova, Gunel Jahangirova, Gabriele Bavota, Vincenzo Riccio, Andrea Stocco, Paolo Tonella
The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance.
1 code implementation • 10 Oct 2019 • Andrea Stocco, Michael Weiss, Marco Calzana, Paolo Tonella
Deep Neural Networks (DNNs) are the core component of modern autonomous driving systems.
Signal Processing
no code implementations • 7 Apr 2017 • Alessio Viticchié, Leonardo Regano, Marco Torchiano, Cataldo Basile, Mariano Ceccato, Paolo Tonella, Roberto Tiella
Obfuscation techniques are a general category of software protections widely adopted to prevent malicious tampering of the code by making applications more difficult to understand and thus harder to modify.
Software Engineering Cryptography and Security