Noureddine Amraoui - Academia.edu (original) (raw)
Uploads
Papers by Noureddine Amraoui
2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)
This paper presents a framework for securing Smart Home Systems (SHSs) automation control. When S... more This paper presents a framework for securing Smart Home Systems (SHSs) automation control. When SHS devices are autonomously controlled by automation apps (called SmartApps), the framework makes sure that only legitimate ones are allowed to automate the SHS. To do so, control commands issued by the SmartApps during regular operation are captured to build a One-Class Support Vector Machine (OCSVM) model as a regular behavior baseline for each installed SmartApp. Then, deviations from this baseline (i.e., anomalous commands) should be detected and rejected, while regular observations (i.e., normal commands) should be considered as legitimate and allowed to be executed. Experimental evaluation conducted on real-world adapted SHS automation history shows the effectiveness of such a behavior-based approach.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Journal of Reliable Intelligent Environments
Bookmarks Related papers MentionsView impact
In complex and pervasive environments, characterized by frequent and unpredictable changes, priva... more In complex and pervasive environments, characterized by frequent and unpredictable changes, privacy and security are the most challenging tasks due to their importance and sensibility. Traditional Schemes of security seems inadequate for these novel challenges. The consideration of the execution context represents a key element for the efficiency of the security policies face to these circumstances. In other words, the system must be context-aware. This paper aims to respond to these novel challenges, by proposing a security policy, based on the `context-aware' notion. The system is conceived as a multi-agents system. The latter is chosen since its mobility and autonomy properties facilitate the achievement of desired objectives. Furthermore, the use of ontology permits to increase the objectivity and eliminate the eventual semantic heterogeneities. The paper presents firstly the general architecture before detailing each one of its components, as well as the distinguished consi...
Bookmarks Related papers MentionsView impact
2020 IEEE Eighth International Conference on Communications and Networking (ComNet), 2020
This paper presents TRICA, a security framework for smart homes. When using controlling apps (e.g... more This paper presents TRICA, a security framework for smart homes. When using controlling apps (e.g., smartphone app), TRICA makes sure that only legitimate users are allowed to control their Internet of Things (IoT) devices. Leveraging User Behavior Analytics (UBA) and Anomaly Detection (AD) techniques, TRI CA collects and processes the historical cyber and physical activities of the user in addition to the historical states of the smart home system to build a One Class Support Vector Machines (OCSVM) model. This model is then used as a baseline from which anomalous commands (i.e., outliers) should be detected and rejected, while normal commands (i.e., targets) should be considered as legitimate and allowed to be executed. Experiments conducted on adapted real-world data properly show the feasibility of such user behavior-based authentication approach. TRICA exhibits low false accept and false reject rates ensuring both security and user convenience, respectively.
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science
Bookmarks Related papers MentionsView impact
International Journal of Information Security
Bookmarks Related papers MentionsView impact
Advanced Information Networking and Applications
Bookmarks Related papers MentionsView impact
International Conference on Advanced Information Networking and Applications, 2019
This paper presents a security framework that continuously authenticates smart homes users in ord... more This paper presents a security framework that continuously authenticates smart homes users in order to make sure that only authorized ones are allowed to control their Internet of Things (IoT) devices while, at the same time, preventing them in case of performing abnormal and dangerous control actions. To do so, control commands under normal operation of both users and devices, are first implicitly traced to build a One Class Support Vector Machine (OCSVM) model as a baseline from which deviations (i.e., anomalous commands) should be detected and rejected, while normal observations (i.e., normal commands) should be considered as legitimate and allowed to be executed. Experiments conducted on our artificial datasets show the efficiency of such user behavior-based approach achieving at least 95.29% and 4.12% of True Positive (TP) and False Positive (FP) rates, respectively.
Bookmarks Related papers MentionsView impact
2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)
This paper presents a framework for securing Smart Home Systems (SHSs) automation control. When S... more This paper presents a framework for securing Smart Home Systems (SHSs) automation control. When SHS devices are autonomously controlled by automation apps (called SmartApps), the framework makes sure that only legitimate ones are allowed to automate the SHS. To do so, control commands issued by the SmartApps during regular operation are captured to build a One-Class Support Vector Machine (OCSVM) model as a regular behavior baseline for each installed SmartApp. Then, deviations from this baseline (i.e., anomalous commands) should be detected and rejected, while regular observations (i.e., normal commands) should be considered as legitimate and allowed to be executed. Experimental evaluation conducted on real-world adapted SHS automation history shows the effectiveness of such a behavior-based approach.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Journal of Reliable Intelligent Environments
Bookmarks Related papers MentionsView impact
In complex and pervasive environments, characterized by frequent and unpredictable changes, priva... more In complex and pervasive environments, characterized by frequent and unpredictable changes, privacy and security are the most challenging tasks due to their importance and sensibility. Traditional Schemes of security seems inadequate for these novel challenges. The consideration of the execution context represents a key element for the efficiency of the security policies face to these circumstances. In other words, the system must be context-aware. This paper aims to respond to these novel challenges, by proposing a security policy, based on the `context-aware' notion. The system is conceived as a multi-agents system. The latter is chosen since its mobility and autonomy properties facilitate the achievement of desired objectives. Furthermore, the use of ontology permits to increase the objectivity and eliminate the eventual semantic heterogeneities. The paper presents firstly the general architecture before detailing each one of its components, as well as the distinguished consi...
Bookmarks Related papers MentionsView impact
2020 IEEE Eighth International Conference on Communications and Networking (ComNet), 2020
This paper presents TRICA, a security framework for smart homes. When using controlling apps (e.g... more This paper presents TRICA, a security framework for smart homes. When using controlling apps (e.g., smartphone app), TRICA makes sure that only legitimate users are allowed to control their Internet of Things (IoT) devices. Leveraging User Behavior Analytics (UBA) and Anomaly Detection (AD) techniques, TRI CA collects and processes the historical cyber and physical activities of the user in addition to the historical states of the smart home system to build a One Class Support Vector Machines (OCSVM) model. This model is then used as a baseline from which anomalous commands (i.e., outliers) should be detected and rejected, while normal commands (i.e., targets) should be considered as legitimate and allowed to be executed. Experiments conducted on adapted real-world data properly show the feasibility of such user behavior-based authentication approach. TRICA exhibits low false accept and false reject rates ensuring both security and user convenience, respectively.
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science
Bookmarks Related papers MentionsView impact
International Journal of Information Security
Bookmarks Related papers MentionsView impact
Advanced Information Networking and Applications
Bookmarks Related papers MentionsView impact
International Conference on Advanced Information Networking and Applications, 2019
This paper presents a security framework that continuously authenticates smart homes users in ord... more This paper presents a security framework that continuously authenticates smart homes users in order to make sure that only authorized ones are allowed to control their Internet of Things (IoT) devices while, at the same time, preventing them in case of performing abnormal and dangerous control actions. To do so, control commands under normal operation of both users and devices, are first implicitly traced to build a One Class Support Vector Machine (OCSVM) model as a baseline from which deviations (i.e., anomalous commands) should be detected and rejected, while normal observations (i.e., normal commands) should be considered as legitimate and allowed to be executed. Experiments conducted on our artificial datasets show the efficiency of such user behavior-based approach achieving at least 95.29% and 4.12% of True Positive (TP) and False Positive (FP) rates, respectively.
Bookmarks Related papers MentionsView impact