Yazar "Kjamilji, Artrim" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim
    Öğe
    A Constant Time Secure and Private Evaluation of Decision Trees in Smart Cities Enabled by Mobile IoT
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kjamilji, Artrim
    A server has an already trained decision tree machine learning model and one or more clients have unclassified query(ies) that they wish to classify using the server's model under strict security, privacy, and efficiency constraints. To do so, already existing secure building blocks are used, improved, and adjusted to fit this scenario. On top of the proposed building blocks, novel secure and private Decision Tree Evaluation (sDTE) algorithms are proposed. The proposed building blocks show better performances than the related ones in literature in terms of computation and communication costs. Consequently, experimental evaluations over benchmark datasets show that the proposed sDTE algorithms build on top of the proposed blocks, also outperform the state-of-the-art ones in terms of computation and communication costs as well as on security and privacy characteristics. Our theoretical analysis shows that if the whole decision tree can fit in a single ciphertext, which in the proposed sDTE algorithms is almost always the case, then private tree evaluations are done in constant time and do not depend on the tree depth. To the best of the author's knowledge, this is the first scheme in literature with such properties.
  • Küçük Resim Yok
    Öğe
    Covert, Secure and Private Communications in Software Defined Networking
    (IEEE Computer Soc, 2023) Kjamilji, Artrim
    Covert and private communications are an essential part of modern Internet. While there have been several works on these topics, almost all of them have one or more drawbacks, which are unacceptable in modern requirements of Software Defined Networking (SDN). To this end, initially, we propose and adopt a few secure buildings blocks, such as secure bit stream match, secure longest prefix match, secure header replication, etc. On top of them we propose covert and secure end-to-end generalized forwarding protocols used in SDN over busy routers. Besides covert communications, communication privacy is a by-product of the proposed protocols. The proposed schemes are proven to be secure under the semi-honest model, outperform in the related schemes in terms of security and privacy characteristics, while the experimental evaluations show their computation and communication efficiency.
  • Küçük Resim
    Öğe
    Highly efficient secure linear algebra for private machine learning classifications over malicious clients in the post-quantum world
    (King Saud bin Abdulaziz University, 2023) Kjamilji, Artrim; Güney, Osman Berke
    Over the last decade there has a been widespread usage of Machine Learning (ML) classifiers in cases such accurate disease diagnosis at clinics, credit card fraud detection in banks, cyber-attacks prevention of computer systems in different industries, etc. However, privacy and security concerns and law regula tions have been an obstacle to the usage of ML classifiers. To this end, this paper addresses the scenario where a server has a private trained ML model, and one or more clients have private queries that they wish to classify using the server’s model. During the process, the server learns nothing, while the clients learn only their final classifications and nothing else. Several ML classification algorithms, such as Deep Neural Networks, Support Vector Machines, Logistic Regression, different flavors of Naïve Bayes, etc., can be expressed in terms of linear algebra operations. To this end, initially, as building blocks, several novel secure linear algebra operations are proposed. On top of them novel secure ML classification algorithms are proposed for the aforementioned classifiers under strict security, privacy and efficiency constraints and their security is proven under the semi-honest model. Since the used underlying cryptographic prim itives are shown to be resilient to quantum computer attacks, the proposed algorithms are also suitable for the post-quantum world. Furthermore, the proposed algorithms are non-interactive and, based on where the bulk of the operations are done, they have the flexibility to be server or client centric. Theoretical analysis and extensive experimental evaluations over benchmark datasets show that the pro posed secure linear algebra operations, hence the secure ML algorithms build on top of them, outperform the state-of-the-art schemes in terms of computation and communication costs as well as on security and privacy characteristics. Moreover, and to the best of the authors’ knowledge, for the first time in literature the security of the proposed algorithms is proven when dealing with multiple malicious clients during classifications.
  • Küçük Resim
    Öğe
    Privacy-Preserving Zero-Sum-Path Evaluation of Decision Tress in Postquantum Industrial IoT
    (IEEE, 2024) Kjamilji, Artrim
    A server has a trained machine learning model in the form of a decision tree (DT), while one or more client(s) have unlabeled queries that they wish to classify using the server's model under strict security, privacy, and efficiency requirements on both sides. To do so, initially, based on lightweight cryptographic primitives, which are shown to be resistant to quantum computer attacks, a few secure buildings are adopted, improved, and adjusted to fit this scenario. On top of them, a novel secure and private DT evaluation and its extension over malicious clients protocols are proposed, which are both proven to be secure. In the process, we use the sum of paths of inner nodes from the root to the leaves of the DT, which in turn utilizes the comparison of threshold values of the tree nodes and the corresponding query feature values (entries). Theoretical analysis and extensive experimental evaluations over benchmark datasets show that the proposed protocols outperform the majority (if not all) of the related state-of-the-art schemes in terms of computation and communication costs as well as on security and privacy characteristics. Furthermore, the proposed protocols are shown to be resistant to side-channel attacks. This makes the proposed protocol suitable for the postquantum world of the industrial Internet of Things, which demands strict security and privacy requirements on devices with restricted hardware/networking resources.