Onur Kardes

Onur Kardes

Auto-generated profile, based on publicly available information

Onur Kardes

Faculty of Engineering, Istanbul Beykent University, Istanbul, Turkey

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2008 in International Journal of Information and Computer Security
Verified
Journal Article
Closed access
MKMurat Kantarcioglu
Murat Kantarcioglu
OKOnur Kardes
Onur Kardes
Most of the cryptographic work in privacy-preserving distributed data mining deals with semi-honest adversaries, which are assumed to follow the prescribed protocol but try to infer private information using the messages they receive during the protocol. Although the semi-honest model is reasonable in some cases, it is unrealistic to assume that adversaries will always follow the protocols exactly. In particular, malicious adversaries could deviate arbitrarily from their prescribed protocols. Secure protocols that are developed against malicious adversaries require utilisation of complex techniques. Clearly, protocols that can withstand malicious adversaries provide more security. However, there is an obvious trade-off: protocols that are secure against malicious adversaries are generally more expensive than those secure against semi-honest adversaries only. In this paper, our goal is to make an analysis of trade-offs between performance and security in privacy-preserving distributed data mining algorithms in the two models. In order to make a realistic comparison, we enhance commonly used subprotocols that are secure in the semi-honest model with zero knowledge proofs to be secure in the malicious model. We compare the performance of these protocols in both models.

1 January 2021 in Turkish Neurosurgery
Verified
Journal Article
Closed access
AAAydin Aydoseli
Aydin Aydoseli
TUTugrul Cem Unal
Tugrul Cem Unal
OKOnur Kardes
Onur Kardes
ODOzge Doguc
Ozge Doguc
IDIlyas Dolas
Ilyas Dolas
ASAltay Sencer
Altay Sencer
To present an early warning system (EWS) that employs a supervised machine learning algorithm for the rapid detection of extra-axial hematomas (EAHs) in an emergency trauma setting. A total of 150 sets of cranial computed tomography (CT) scans were used in this study with a total of 11,025 images. Of the CTs, 75 were labeled as EAH, the remaining 75 were normal. A random forest algorithm was utilized for the detection of EAHs. The CTs were randomized into two groups: 100 samples for training of the algorithm (split evenly between EAH and normal cases), and 50 samples for testing. In the training phase, the algorithm scanned every CT slice separately for image features such as entropy, moment, and variance. If the algorithm determined an EAH on two or more images in a CT set, then the workflow produced an alert in the form of an email. Data from 50 patients (25 EAH and 25 controls) were used for testing the EWS. For all CTs with an EAH, an alert was produced, with a 0% false-negative rate. For 16% of the cases, the practitioner received an email from the EWS that the patient might have an EAH despite having a normal CT scan. Positive and negative predictive values were 86% and 100%, respectively. An EWS based on a machine learning algorithm is an efficient and inexpensive way of facilitating the work of emergency practitioners such as emergency physicians, neuroradiologists, and neurosurgeons.

1 October 2007
Verified
Conference Paper
Closed access
MKMurat Kantarcioglu
Murat Kantarcioglu
OKOnur Kardes
Onur Kardes
Although the semi-honest model is reasonable in some cases, it is unrealistic to assume that adversaries will al- ways follow the protocols exactly. In particular, malicious adversaries could deviate arbitrarily from their prescribed protocols. Clearly, protocols that can withstand malicious adversaries provide more security. However, there is an ob- vious trade-off: protocols that are secure against malicious adversaries are generally more expensive than those secure against semi-honest adversaries only. In this paper, our goal is to make an analysis of trade-offs between perfor- mance and security in privacy-preserving distributed data mining algorithms in the two models. In order to make a realistic comparison, we enhance commonly used subpro- tocols that are secure in the semi-honest model with zero knowledge proofs to be secure in the malicious model. We compare the performance of these protocols in both models.

17 January 2026 in Decision Making Advances
Verified
Journal Article
Open access
PDF file
ÖEÖznur Gülen Ertosun
Öznur Gülen Ertosun
SESerkan Eti
Serkan Eti
ODOzge Doguc
Ozge Doguc
SYSerhat YUKSEL
Serhat YUKSEL
HDHasan Dincer
Hasan Dincer
OKOnur Kardeş
Onur Kardeş
In the context of the Life 3.0 paradigm, where digitalization is accelerating, determining the most appropriate innovative working model for different sectors has become a strategic imperative. However, the literature lacks integrated multi-criteria approaches for evaluating the effectiveness of alternative working models, such as freelance, hybrid, remote, and metaverse-based models, within a sectoral context. This study aims to determine the most appropriate working model based on the structural, digital, and operational characteristics of different sectors and to identify the criteria that should be prioritized in this decision-making process. The Information and Technology, Education and Consulting, Marketing and E-Commerce, and Finance and Insurance sectors are analyzed. First, 17 criteria affecting the selection of working models are identified. Publications indexed in the Web of Science (WoS) database are scanned using a Robotic Process Automation (RPA) approach, and the eight most frequent and relevant criteria are selected using text mining techniques. Data obtained from interviews with five experts are then weighted according to the experts' demographic characteristics using a dimensionality reduction method. The criteria weights are determined using the SITDE method, while the alternatives are ranked using the RATGOS algorithm. In addition, a novel fuzzy set system, Behavioral Leadership Fuzzy Sets (BLFSs), is developed and integrated into the model to analyze the impact of decision-maker behaviors on managerial reflexes. The proposed framework integrates artificial intelligence and multi-criteria decision-making techniques, reduces subjectivity through data-driven criteria selection and expert weighting, and incorporates behavioral leadership characteristics into the decision process. The findings indicate that the hybrid model is the most appropriate working model across all four sectors. However, sectoral priorities differ: career and development opportunities are the most important criterion in the IT sector, whereas market access and ethical responsibilities are prioritized in the finance sector.

24 August 2026 in Sustainable Futures
Verified
Journal Article
Open access
SYSerhat YUKSEL
Serhat YUKSEL
SESerkan Eti
Serkan Eti
HDHasan Dincer
Hasan Dincer
MAMerve Acar
Merve Acar
EEEdanur Ergün
Edanur Ergün
ODOzge Doguc
Ozge Doguc

10 January 2026
Verified
Book Chapter
Closed access
PDF file
ODOzge Doguc
Ozge Doguc
Gokhan SILAHTAROGLUGokhan SILAHTAROGLU
Gokhan SILAHTAROGLU
OKOnur Kardes
Onur Kardes