FedREVAN: real-time detection of vulnerable Android source code through federated neural network with XAI

Conference paper


Senanayake, J., Kalutarage, H., Petrovski, A., Al-Kadri, M.O. and Piras, L. 2023. FedREVAN: real-time detection of vulnerable Android source code through federated neural network with XAI. ESORICS Workshop on Attacks and Software Protection (WASP). The Hague, The Netherlands 25 - 29 Sep 2023 Springer.
TypeConference paper
TitleFedREVAN: real-time detection of vulnerable Android source code through federated neural network with XAI
AuthorsSenanayake, J., Kalutarage, H., Petrovski, A., Al-Kadri, M.O. and Piras, L.
Abstract

Adhering to security best practices during the development of Android applications is of paramount importance due to the high prevalence of apps released without proper security measures. While automated tools can be employed to address vulnerabilities during development, they may prove to be inadequate in terms of detecting vulnerabilities. To address this issue, a federated neural network with XAI, named FedREVAN, has been proposed in this study. The initial model was trained on the LVDAndro dataset and can predict potential vulnerabilities with a 96% accuracy and 0.96 F1-Score for binary classification. Moreover, in case the code is vulnerable, FedREVAN can identify the associated CWE category with 93% accuracy and 0.91 F1-Score for multi-class classification. The initial neural network model was released in a federated environment to enable collaborative training and enhancement with other clients. Experimental results demonstrate that the federated neural network model improves accuracy by 2% and F1-Score by 0.04 in multi-class classification. XAI is utilised to present the vulnerability detection results to developers with prediction probabilities for each word in the code. The FedREVAN model has been integrated into an API and further incorporated into Android Studio to provide real-time vulnerability detection. The FedREVAN model is highly efficient, providing prediction probabilities for one code line in an average of 300 milliseconds.

Keywordsandroid application security; code vulnerability; neural network; federated learning; XAI
Sustainable Development Goals9 Industry, innovation and infrastructure
Middlesex University ThemeCreativity, Culture & Enterprise
LanguageEnglish
ConferenceESORICS Workshop on Attacks and Software Protection (WASP)
Proceedings TitleESORICS Workshop on Attacks and Software Protection (WASP) Proceedings
PublisherSpringer
Publication process dates
Accepted15 Aug 2023
Deposited10 Nov 2023
Output statusAccepted
Permalink -

https://repository.mdx.ac.uk/item/wqxx6

Restricted files

Accepted author manuscript

  • 68
    total views
  • 1
    total downloads
  • 3
    views this month
  • 0
    downloads this month

Export as

Related outputs

Android code vulnerabilities early detection using AI-powered ACVED plugin
Senanayake, J., Kalutarage, H., Al-Kadri, M.O., Petrovski, A. and Piras, L. 2023. Android code vulnerabilities early detection using AI-powered ACVED plugin. Atluri, V. and Ferrara, A. (ed.) 37th Annual IFIP WG 11.3 Conference (DBSec 2023). Sophia-Antipolis, France 19 - 21 Jul 2023 Cham Springer. pp. 339–357 https://doi.org/10.1007/978-3-031-37586-6_20
Labelled vulnerability dataset on Android source code (LVDAndro) to develop AI-based code vulnerability detection models
Senanayake, J., Kalutarage, H., Al-Kadri, M.O., Piras, L. and Petrovski, A. 2023. Labelled vulnerability dataset on Android source code (LVDAndro) to develop AI-based code vulnerability detection models. International Conference on Security and Cryptography (SECRYPT) 2023. Rome, Italy 10 - 12 Jul 2023 Rome (IT) SciTePress. pp. 659-666 https://doi.org/10.5220/0012060400003555
Goal-modeling privacy-by-design patterns for supporting GDPR compliance
Al-Obeidallah, M., Piras, L., Iloanugo, O., Mouratidis, H., Alkubaisy, D and Dellagiacoma, D. 2023. Goal-modeling privacy-by-design patterns for supporting GDPR compliance. International Conference on Software Technologies (ICSOFT). Rome (Italy) 10 - 12 Jul 2023 Rome (IT) SciTePress. https://doi.org/10.5220/0012080700003538
Android source code vulnerability detection: a systematic literature review
Senanayake, J., Kalutarage, H., Al-Kadri, M.O., Petrovski, A. and Piras, L. 2023. Android source code vulnerability detection: a systematic literature review. ACM Computing Surveys. 55 (9). https://doi.org/10.1145/3556974
Supporting the individuation, analysis and gamification of software components for acceptance requirements fulfilment
Calabrese, F., Piras, L. and Giorgini, P. 2022. Supporting the individuation, analysis and gamification of software components for acceptance requirements fulfilment. Barn, B. and Sandkuhl, K (ed.) IFIP Working Conference on The Practice of Enterprise Modeling. London 23 - 25 Nov 2022 Springer. pp. 33-48 https://doi.org/10.1007/978-3-031-21488-2_3
Goal models for acceptance requirements analysis and gamification design
Piras, L., Paja, E., Giorgini, P. and Mylopoulos, J. 2017. Goal models for acceptance requirements analysis and gamification design. Mayr, H.C., Guizzardi, G., Ma, H. and Pastor, O. (ed.) 36th International Conference on Conceptual Modeling. Valencia 2017 Cham Springer. pp. 223-230 https://doi.org/10.1007/978-3-319-69904-2_18
Using gamification to incentivize sustainable urban mobility
Kazhamiakin, Raman, Marconi, Annapaola, Perillo, Mirko, Pistore, Marco, Valetto, Giuseppe, Piras, Luca, Avesani, Francesco and Perri, Nicola 2015. Using gamification to incentivize sustainable urban mobility. IEEE International Smart Cities Conference. IEEE. https://doi.org/10.1109/ISC2.2015.7366196