Nga Nguyen is Associate Professor in Computer Science at ESILV and member of the Digital Group. Her research interests include software verification, safety and security of embedded systems.
Nga Nguyen; Michel Batteux; Antoine Rauzy
Modeling Cyberattack Propagation and Impacts on Cyber-Physical System Safety: An Experiment Article de journal
Dans: Electronics, vol. 12, no. 1, p. 77, 2022.
@article{nguyen_2072,
title = {Modeling Cyberattack Propagation and Impacts on Cyber-Physical System Safety: An Experiment},
author = {Nga Nguyen and Michel Batteux and Antoine Rauzy},
url = {https://www.mdpi.com/2079-9292/12/1/77},
year = {2022},
date = {2022-12-01},
journal = {Electronics},
volume = {12},
number = {1},
pages = {77},
abstract = {In this article, we present an experiment we conducted with discrete event simulations
to analyze the effects of multi-step cyberattacks on the safety of cyber-physical systems. We show how to represent systems, their components (either software and/or hardware), communication links, security measures, and attacks from a malicious intruder. The latter are typically taken from the MITRE ATT&CK knowledge base. The discrete event simulation method makes it possible to represent any event affecting the system. We illustrate our approach by means of an illustrative example involving cyberattacks against the navigation system of an autonomous ship. We show how the formal modeling language AltaRica, primarily dedicated to safety analyses, can assess this illustrative example by representing the system and automatically extracting sequences of attacks,
leading to a safety-critical situation, namely the deviation of the ship by the attacker. This article aims to discuss this approach and to outline the lessons learned from our experience.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ihab Taleb; Guillaume Guérard; Nga Nguyen; Frédéric Fauberteau
A Flexible Deep Learning Method for Energy Forecasting Article de journal
Dans: Energies, vol. 15, no. 11, p. 3926, 2022.
@article{taleb_1836,
title = {A Flexible Deep Learning Method for Energy Forecasting},
author = {Ihab Taleb and Guillaume Guérard and Nga Nguyen and Frédéric Fauberteau},
url = {https://www.mdpi.com/1996-1073/15/11/3926},
year = {2022},
date = {2022-05-01},
journal = {Energies},
volume = {15},
number = {11},
pages = {3926},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Saoussen Mili; Nga Nguyen; Rachid Chelouah
Model-Driven Architecture Based Security Analysis Article de journal
Dans: Systems Engineering, vol. 24, no. 5, p. 307-321, 2021.
@article{mili_1606,
title = {Model-Driven Architecture Based Security Analysis},
author = {Saoussen Mili and Nga Nguyen and Rachid Chelouah},
url = {https://onlinelibrary.wiley.com/doi/10.1002/sys.21581},
year = {2021},
date = {2021-09-01},
journal = {Systems Engineering},
volume = {24},
number = {5},
pages = {307-321},
abstract = {This paper proposes a Model-Driven Architecture approach for the development of an embedded system validation platform namely Model-Based Security Analysis for Embedded Systems (MBSAES). The security properties are formally modeled and verified at an early stage of the design process of the system, which helps to reduce late errors and development time. A separation of the attack scenarios and the system design from the implementation details has been respected. To transform semi-formal models from SysML to NuSVM model checking platform, two Model-to-Text, horizontal and exogenous transformations have been implemented. The first one employs a programming approach with Java to create a Computational Tree Logic specification from an Extended Attack Tree, whereas the second one uses a template approach with Acceleo to generate NuSMV code from SysML structural and behavioral models. To illustrate our approach, a case study, involving attacks aiming to unlock car door systems, via signal jamming and code replaying, is considered. The results of this research will contribute to the automatic validation of system designs against security vulnerabilities via a database of extended attack trees building from existing atomic attacks.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Théo Serru; Nga Nguyen; Michel Batteux; Antoine Rauzy; Raphaël Blaize; Laurent Sagaspe; Emmanuel Arbaretier
Discussions About Model Based Security for Cyber Physical Systems Conférence
Congrès de maîtrise des risques et de sûreté de fonctionnement, Paris, France, 2022.
@conference{serru_1806,
title = {Discussions About Model Based Security for Cyber Physical Systems},
author = {Théo Serru and Nga Nguyen and Michel Batteux and Antoine Rauzy and Raphaël Blaize and Laurent Sagaspe and Emmanuel Arbaretier},
url = {https://www.imdr-lambdamu.eu/},
year = {2022},
date = {2022-10-01},
booktitle = {Congrès de maîtrise des risques et de sûreté de fonctionnement},
address = {Paris, France},
abstract = {Cyber-Physical Systems (CPSs) are intensively used in many different kinds of industrial
systems. Whether you are driving a recent car, taking the plane, having a smartphone or smart watch, you interact with CPSs. If we sometimes feel more comfortable or secure with them, these systems are very exposed to cyber-attacks. This is due to their highly interconnected nature and implies that they need to be carefully protected. Thus, one of their main challenges is to ensure their security.
Recent years have seen an increasing concern about the cybersecurity of CPSs and many methods have been developed to answer their challenges.
In this article, we focus on a recent philosophy of doing cybersecurity, inspired by Model
Based System Engineering (MBSE), called Model Based Security (MBS) or Model Driven Security [1]. This specialization of MBSE has been first applied to IT systems and is now a growing research field for CPSs as it helps to automatize cybersecurity assessments that are quickly intractable for engineers working on complex systems.
Despite the growing interest regarding MBS for CPSs, this method is poorly applied in
industry. Most of the works have been made in research labs and have not yet reached industrial application level. Furthermore, these works are relatively diverse and focus on different fields or different aspects of security. This variety is a chance and a problem because there is no consensus in the community on how to apply MBS to CPSs. Indeed, there is no established formal way to define systems (especially the interactions between the physical and cyber layer), threat models, scenarios of
attacks (qualitative analysis), potentiality evaluation (quantitative analysis), deployment phases, etc. [1] [2]. In addition, the abstraction is too high level to describe the complex interactions involved in CPSs or too low level to handle complexity [3].
The major contribution of this work is thus to summarize the actual strengths and weaknesses
of MBS for CPS. To do so, we propose to dig into some recent works and analyze them to understand the needs and missing theoretical background in this field. Then, with a clear overview of the issues about MBS, we will identify some solutions or trigger points that might help to make this type of
approach more attractive and exhaustive.
Finally, it will be possible to introduce an approach allowing MBS for CPS with the concern to cover some challenges of MBS for CPS with a simplistic, yet comprehensive, formalism.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Ihab Taleb; Guillaume Guérard; Frédéric Fauberteau; Nga Nguyen
A Holonic Smart Grid Model for Isolated Areas Conférence
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, PhD Forum, Grenoble, France, 2022.
@conference{taleb_1934,
title = {A Holonic Smart Grid Model for Isolated Areas},
author = {Ihab Taleb and Guillaume Guérard and Frédéric Fauberteau and Nga Nguyen},
url = {https://2022.ecmlpkdd.org/index.php/phd-forum/},
year = {2022},
date = {2022-09-01},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, PhD Forum},
address = {Grenoble, France},
abstract = {Since the beginning of the $21$st century, smart grid models are gaining more and more importance as they play a major role in the demand side management and the flexible integration of renewable energy sources. Indeed, diverse architectures and models have been proposed for smart grids. In this paper, we propose a model composed of two parts, the first part is to optimize, on a weekly scale, thermal generation, and energy storage while prioritizing renewable energy sources to minimize global costs and global warming effects. The second part consists of, having optimized production and storage, the negotiation between neighboring holons on the same level using evolutionary game theory, combined with simulated annealing and Q-learning approaches to ensure a back and forth between the various levels.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Ihab Taleb; Guillaume Guérard; Frédéric Fauberteau; Nga Nguyen
A holonic multi-agent architecture for smart grids Inproceedings
Dans: International Conference on Agents and Artificial Intelligence, Lisbon, Portugal, 2023, ISBN: 978-989-758-547-0.
@inproceedings{taleb_2073,
title = {A holonic multi-agent architecture for smart grids},
author = {Ihab Taleb and Guillaume Guérard and Frédéric Fauberteau and Nga Nguyen},
url = {https://icaart.scitevents.org/},
issn = {978-989-758-547-0},
year = {2023},
date = {2023-02-01},
booktitle = {International Conference on Agents and Artificial Intelligence},
address = {Lisbon, Portugal},
abstract = {The global warming and the increase of fossil fuel prices make the minimization of energy generation an important objective. Thus, smart grids are becoming more and more relevant in a context where we want to regulate the demand according to the available energy. This regulation can be operated thanks to Demand Side Management (DSM) tools. While different models and architectures have been developed for smart grids, only few papers used holonic architectures. For this, we propose in this paper a holonic architecture for smart grids. This type of architectures is relevant to smart grids as it allow the various actors in the grids to work even in the cases of technical problems. Holons in the proposed model are composed of five interconnecting agents that ensure flexibility on the various aspects. This model has been tested and has proven to work on 3 different scenarios. The first scenario simulates a grid in its healthy state. The second one simulates a grid where a region can be disconnected from a blackout for example. The third one simulates a grid with production mismanagement. Results show how the grid distributes the available energy depending on the available production, priorities (if any) and the assurance of the distribution across the various requesting holons.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ihab Taleb; Guillaume Guérard; Frédéric Fauberteau; Nga Nguyen
A holonic multi-agent architecture for smart grids Inproceedings
Dans: 15th International Conference on Agents and Artificial Intelligence, Lisbon, Portugal, 2023.
@inproceedings{taleb_2237,
title = {A holonic multi-agent architecture for smart grids},
author = {Ihab Taleb and Guillaume Guérard and Frédéric Fauberteau and Nga Nguyen},
url = {http://www.wikicfp.com/cfp/servlet/event.showcfp?copyownerid=90704&eventid=167079},
year = {2023},
date = {2023-02-01},
booktitle = {15th International Conference on Agents and Artificial Intelligence},
address = {Lisbon, Portugal},
abstract = {The global warming and the increase of fossil fuel prices make the minimization of energy generation animportant objective. Thus, smart grids are becoming more and more relevant in a context where we want toregulate the demand according to the available energy. This regulation can be operated thanks to Demand SideManagement (DSM) tools. While different models and architectures have been developed for smart grids,only few papers used holonic architectures. For this, we propose in this paper a holonic architecture for smartgrids. This type of architectures is relevant to smart grids as it allows the various actors in the grids to workeven in the cases of technical problems. Holons in the proposed model are composed of five interconnectingagents that ensure flexibility on the various aspects. This model has been tested and has proven to work on3 different scenarios. The first scenario simulates a grid in its healthy state. The second one simulates agrid where a region can be disconnected from a blackout for example. The third one simulates a grid withproduction mismanagement. Results show how the grid distributes the available energy depending on theavailable production, priorities (if any) and the assurance of the distribution across the various requestingholons.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Guillaume Guérard; Ihab Taleb; Nga Nguyen; Frédéric Fauberteau
Modélisation Multi-Agent pour les Réseaux Energétique Insulaires Inproceedings
Dans: Journées Francophones sur les Systèmes Multi-Agents, Saint-Etienne, France, 2022.
@inproceedings{guerard_1831,
title = {Modélisation Multi-Agent pour les Réseaux Energétique Insulaires},
author = {Guillaume Guérard and Ihab Taleb and Nga Nguyen and Frédéric Fauberteau},
url = {https://ci.mines-stetienne.fr/pfia2022/conferences/jfsma/},
year = {2022},
date = {2022-06-01},
booktitle = {Journées Francophones sur les Systèmes Multi-Agents},
address = {Saint-Etienne, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Adam Talbi; Arthur Viens; Louis-Clément Leroux; Morgane François; Mathias Caillol; Nga Nguyen
Feature Importance And Deep Learning For Android Malware Detection Inproceedings
Dans: International Conference on Information Systems Security and Privacy, Vienna, Austria, 2022.
@inproceedings{talbi_1741,
title = {Feature Importance And Deep Learning For Android Malware Detection},
author = {Adam Talbi and Arthur Viens and Louis-Clément Leroux and Morgane François and Mathias Caillol and Nga Nguyen},
url = {https://icissp.scitevents.org/Home.aspx},
year = {2022},
date = {2022-02-01},
booktitle = {International Conference on Information Systems Security and Privacy},
address = {Vienna, Austria},
abstract = {Effective and efficient malware detection is key in today's world to prevent systems from being compromised, to protect personal user data, and to tackle other security issues. In this paper, we worked on Android malware detection by using static analysis features and deep learning methods to separate benign applications from malicious ones. Custom feature vectors are extracted from the Drebin and the AndroZoo dataset and different data science methods of feature importance are used to improve the results of Deep Neural Network classification.
Experimental results on the Drebin dataset were significant with 99.31% accuracy in malware detection. We extended our work on more recent applications with a complete pipeline for the AndroZoo dataset, with about 40,000 APKs used from 2014 to 2021 pre-tagged as reported malicious or not. The pipeline includes static features extracted from the manifest file and bytecode such as suspicious behaviors, restricted and suspicious API calls, etc. The accuracy result for AndroZoo is 97.7%, confirming the power of deep learning on Android malware detection.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nga Nguyen
RobAFIS: Lessons Learned from a Robotic Systems Engineering Challenge Inproceedings
Dans: 2021 International Symposium on Systems Engineering Proceedings, Vienna, Austria, 2021.
@inproceedings{nguyen_1596,
title = {RobAFIS: Lessons Learned from a Robotic Systems Engineering Challenge},
author = {Nga Nguyen},
url = {https://2021.ieeeisse.org/wp-content/uploads/sites/37/2021/08/ISSE_2021_Program-02.pdf},
year = {2021},
date = {2021-09-01},
booktitle = {2021 International Symposium on Systems Engineering Proceedings},
address = {Vienna, Austria},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
No posts by this author.
N'hésitez pas à contacter le service des admissions pour tout renseignement complémentaire :
