![](bg8.png)
Table 3: The confusion matrix of the classifier for 6 applications running with various platform OSs and training data sets.
APP 1 APP 2 APP 3 APP 5 APP 6 APP 7 mean (%) ± std
APP 1 1529 0 209 0 22 0 86.7 ± 0.15
APP 2 0 1760 0 0 0 0 100 ± 0
APP 3 0 0 1623 137 0 0 92.2 ± 0.15
APP 5 0 0 61 1483 216 0 84.2 ± 0.21
APP 6 0 0 0 0 1760 0 100 ± 0
APP 7 0 0 0 0 0 1760 100 ± 0
93.85
allow us to build richer signatures and reduce inaccu-
racy of classification. Additionally we want to extend
our architecture to include intrusion detection mod-
ules, which will not simply classify an application as
being authorized or not, but also try to determine its
behaviour at runtime.
ACKNOWLEDGEMENTS
This paper builds upon the work done within the
Dutch NWO Research project ‘Data Logistics for Lo-
gistics Data’ (DL4LD, www.dl4ld.net), supported by
the Dutch Top consortia for Knowledge and Innova-
tion ‘Institute for Advanced Logistics‘ (TKI Dinalog,
www.dinalog.nl) of the Ministry of Economy and En-
vironment in The Netherlands and the Dutch Commit-
to-Data initiative (https://commit2data.nl/).
REFERENCES
Canon, R. S. and Younge, A. (2019). A case for porta-
bility and reproducibility of hpc containers. In 2019
IEEE/ACM International Workshop on Containers
and New Orchestration Paradigms for Isolated Envi-
ronments in HPC (CANOPIE-HPC), pages 49–54.
Das, P. K., Joshi, A., and Finin, T. (2017). App behavioral
analysis using system calls. In 2017 IEEE Confer-
ence on Computer Communications Workshops, IN-
FOCOM WKSHPS 2017, pages 487–492. Institute of
Electrical and Electronics Engineers Inc.
Forrest, S., Hofmeyr, S., and Somayaji, A. (2008). The evo-
lution of system-call monitoring. In 2008 annual com-
puter security applications conference (acsac), pages
418–430. IEEE.
Forrest, S., Hofmeyr, S. A., Somayaji, A., and Longstaff,
T. A. (1996). A sense of self for unix processes. In
Proceedings 1996 IEEE Symposium on Security and
Privacy, pages 120–128. IEEE.
Hofmeyr, S. A., Forrest, S., and Somayaji, A. (1998). Intru-
sion detection using sequences of system calls. Jour-
nal of computer security, 6(3):151–180.
Khreich, W., Khosravifar, B., Hamou-Lhadj, A., and Talhi,
C. (2017). An anomaly detection system based on
variable n-gram features and one-class svm. Informa-
tion and Software Technology, 91:186–197.
Merkel, D. (2014). Docker: lightweight linux containers for
consistent development and deployment. Linux jour-
nal, 2014(239):2.
Paek, S.-H., Oh, Y.-K., Yun, J., and Lee, D.-H. (2006). The
architecture of host-based intrusion detection model
generation system for the frequency per system call.
In 2006 International Conference on Hybrid Informa-
tion Technology, volume 2, pages 277–283. IEEE.
Subba, B., Biswas, S., and Karmakar, S. (2017). Host based
intrusion detection system using frequency analysis of
n-gram terms. In TENCON 2017-2017 IEEE Region
10 Conference, pages 2006–2011. IEEE.
Suratkar, S., Kazi, F., Gaikwad, R., Shete, A., Kabra, R.,
and Khirsagar, S. (2019). Multi hidden markov mod-
els for improved anomaly detection using system call
analysis. In 2019 IEEE Bombay Section Signature
Conference (IBSSC), pages 1–6. IEEE.
Varghese, S. M. and Jacob, K. P. (2007). Process profiling
using frequencies of system calls. In The Second In-
ternational Conference on Availability, Reliability and
Security (ARES’07), pages 473–479. IEEE.
Xiao, X., Zhang, S., Mercaldo, F., Hu, G., and Sangaiah,
A. K. (2019). Android malware detection based on
system call sequences and lstm. Multimedia Tools and
Applications, 78(4):3979–3999.
Zhang, L., Cushing, R., Gommans, L., De Laat, C.,
and Grosso, P. (2019). Modeling of collaboration
archetypes in digital market places. IEEE Access,
7:102689–102700.
Profiling and Discriminating of Containerized ML Applications in Digital Data Marketplaces (DDM)
515