- author = "Claudio Ferretti and Martina Saletta",
- title = "Deceiving Neural Source Code Classifiers: Finding Adversarial Examples with Grammatical Evolution",
- booktitle = "Genetic and Evolutionary Computation in Defense, Security, and Risk",
- year = "2021",
- editor = "Riyad Alshammari and Erik Hemberg and Tokunbo Makanju",
- pages = "1889--1897",
- address = "internet",
- series = "GECCO '21",
- month = jul # " 10-14",
- organisation = "SIGEVO",
- publisher = "Association for Computing Machinery",
- publisher_address = "New York, NY, USA",
- keywords = "genetic algorithms, genetic programming, Grammatical Evolution, ANN, deep learning, adversarial examples, computer security, security assessment",
- isbn13 = "978-1-4503-8351-6",
-
DOI = "
doi:10.1145/3449726.3463222",
- size = "9 pages",
-
abstract = "an evolutionary approach for assessing the robustness
of a system trained in the detection of software
vulnerabilities. By applying a Grammatical Evolution
genetic algorithm, and using the output of the system
being assessed as the fitness function, we show how we
can easily change the classification decision (i.e.
vulnerable or not vulnerable) for a given instance by
simply injecting evolved features that in no wise
affect the functionality of the program. Additionally,
by means of the same technique, that is by simply
modifying the program instances, we show how we can
significantly decrease the accuracy measure of the
whole system on the dataset used for the test
phase.
Finally we remark that these methods can be easily customized for applications in different domains and also how the underlying ideas can be exploited for different purposes, such as the exploration of the behaviour of a generic neural system.",
-
notes = "Universita degli Studi di Milano-Bicocca
GECCO-2021 A Recombination of the 30th International Conference on Genetic Algorithms (ICGA) and the 26th Annual Genetic Programming Conference (GP)",
