activity
20142023
most citedOperation is the hardest teacher: estimating DNN accuracy looking for mispredictions

21 citations · 54 across the 5 of their papers we have counts for

collaborators

5 papers

cs.SE2023★ 4 cited

Reasoning-Based Software Testing

Luca Giamattei, Roberto Pietrantuono, Stefano Russo

With software systems becoming increasingly pervasive and autonomous, our ability to test for their quality is severely challenged. Many systems are called to operate in uncertain…

cs.LG2023★ 5 cited

Iterative Assessment and Improvement of DNN Operational Accuracy

Antonio Guerriero, Roberto Pietrantuono, Stefano Russo

Deep Neural Networks (DNN) are nowadays largely adopted in many application domains thanks to their human-like, or even superhuman, performance in specific tasks. However, due to u…

cs.SE2021★ 20 cited

Software Micro-Rejuvenation for Android Mobile Systems

Domenico Cotroneo, Luigi De Simone, Roberto Natella +2

Software aging -- the phenomenon affecting many long-running systems, causing performance degradation or an increasing failure rate over mission time, and eventually leading to fai…

cs.SE2021★ 21 cited

Operation is the hardest teacher: estimating DNN accuracy looking for mispredictions

Antonio Guerriero, Roberto Pietrantuono, Stefano Russo

Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real world data (operational dataset), from which a subset is selected, manually labelle…

cs.SE2014★ 4 cited

Big Data in Critical Infrastructures Security Monitoring: Challenges and Opportunities

L. Aniello, A. Bondavalli, A. Ceccarelli +8

Critical Infrastructures (CIs), such as smart power grids, transport systems, and financial infrastructures, are more and more vulnerable to cyber threats, due to the adoption of c…