Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Search Results

Now showing 1 - 2 of 2
  • Conference Object
    Citation - WoS: 3
    Citation - Scopus: 7
    A Taxonomic Survey of Model Extraction Attacks
    (IEEE, 2023) Genç, Didem; Özuysal, Mustafa; Tomur, Emrah
    A model extraction attack aims to clone a machine learning target model deployed in the cloud solely by querying the target in a black-box manner. Once a clone is obtained it is possible to launch further attacks with the aid of the local model. In this survey, we analyze existing approaches and present a taxonomic overview of this field based on several important aspects that affect attack efficiency and performance. We present both early works and recently explored directions. We conclude with an analysis of future directions based on recent developments in machine learning methodology.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 3
    Context-Aware Operation-Based Access Control for Internet of Things Applications
    (Institute of Electrical and Electronics Engineers Inc., 2019) Genç, Didem; Tomur, Emrah; Erten, Yusuf Murat
    Recently, interest of both the academic and industrial world in Internet of Things (IoT) has been increasing and this trend requires development of new security approaches addressing potential weaknesses in this domain. Despite the presence of many studies directed towards security of IoT applications, they are mostly adoption of current methods to IoT scenarios. Yet, IoT applications are comprised of various kinds of different entities including computers, processes, people and services. Therefore, it is inadequate to detect malicious attempts by using conventional security methods, which apply fixed security policies and do not take interaction of things, that is context information, into account. In this study, by considering new security requirements of next generation IoT applications, we propose a fine-grained, dynamic and easily manageable access control model, which is called context-aware operation-based access control.