FormaliSE 2020 keynote: Corina Pasareanu
FormaliSE 2020 was organised as a 1-day virtual conference co-located with ICSE on July 13, 2020. The main objective of FormaliSE is to foster the integration between the formal methods and the software engineering communities, to strengthen the – still too weak – links between them, and to stimulate researchers to share ideas, techniques, and results, with the ultimate goal to propose novel solutions to the fraught problem of improving the quality of software systems. We here bring you a keynote from Formalise 2020, given by Corina Pasareanu: On the Probabilistic Analysis of Neural Networks.
Assoc. Prof. Corina Pasareanu (Carnegie
Mellon University ) gave the
FormaliSE 2020 keynote "On the Probabilistic Analysis of Neural Networks"
Neural networks are powerful tools for automated decision-making, seeing increased application in safety-critical domains, such as autonomous driving. Due to their black-box nature and large scale, reasoning about their behavior is challenging. Statistical analysis is often used to infer probabilistic properties of a network, such as its robustness to noise and inaccurate inputs. While scalable, statistical methods can only provide probabilistic guarantees on the quality of their results and may underestimate the impact of low probability inputs leading to undesired behavior of the network. We investigate here the use of symbolic analysis and constraint solution space quantification to precisely quantify probabilistic properties in neural networks. We demonstrate the potential of the proposed technique in a case study involving the analysis of ACAS-Xu, a collision avoidance system for unmanned aircraft control.
Corina Pasareanu is an Associate Research Professor with CyLab at Carnegie Mellon University, working at the Silicon Valley campus with NASA Ames Research Center. Her research interests include: model checking and automated testing, compositional verification, model-based development, probabilistic software analysis, and autonomy and Security. She is the recipient of several awards, including ASE Most Influential Paper Award (2018), ESEC/FSE Test of Time Award (2018), ISSTA Retrospective Impact Paper Award (2018), ACM Distinguished Scientist (2016), ACM Impact Paper Award (2010), ICSE 2010 Most Influential Paper Award (2010).