Reference : Training binary classifiers as data structure invariants

	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/41037

Title :	Training binary classifiers as data structure invariants
Language :	English
Author, co-author :	Molina, Facundo [> >]
	Degiovanni, Renzo Gaston [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) >]
	Ponzio, Pablo [> >]
	Regis, Germán [> >]
	Aguirre, Nazareno [> >]
	Frias, Marcelo F. [> >]
Publication date :	2019
Main document title :	Proceedings of the 41st International Conference on Software Engineering ICSE 2019, Montreal, QC, Canada, May 25-31, 2019
Pages :	759 - 770
Peer reviewed :	Yes
On invitation :	No
Audience :	International
Event name :	41st International Conference on Software Engineering ICSE 2019
Event date :	May 25-31, 2019
Abstract :	[en] We present a technique that enables us to distinguish valid from invalid data structure objects. The technique is based on building an artificial neural network, more precisely a binary classifier, and training it to identify valid and invalid instances of a data structure. The obtained classifier can then be used in place of the data structure’s invariant, in order to attempt to identify (in)correct behaviors in programs manipulating the structure. In order to produce the valid objects to train the network, an assumed-correct set of object building routines is randomly executed. Invalid instances are produced by generating values for object fields that “break” the collected valid values, i.e., that assign values to object fields that have not been observed as feasible in the assumed-correct program executions that led to the collected valid instances. We experimentally assess this approach, over a benchmark of data structures. We show that this learning technique produces classifiers that achieve significantly better accuracy in classifying valid/invalid objects compared to a technique for dynamic invariant detection, and leads to improved bug finding.
Target :	Researchers ; Professionals ; Students ; General public
Permalink :	http://hdl.handle.net/10993/41037
DOI :	10.1109/ICSE.2019.00084
Other URL :	https://doi.org/10.1109/ICSE.2019.00084
Commentary :	759--770
FnR project :	FnR ; FNR12632675 > Michail Papadakis > SATOCROSS > Support of Advanced Test cOverage Criteria for RObust and Secure Software > 01/01/2019 > 31/12/2021 > 2018

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access learning-invariants.pdf Author preprint 466 kB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map