no code implementations • 24 Jan 2024 • Ignacio Segovia-Dominguez, Yuzhou Chen, Cuneyt G. Akcora, Zhiwei Zhen, Murat Kantarcioglu, Yulia R. Gel, Baris Coskunuzer
This framework empowers the exploration of data by simultaneously varying multiple scale parameters.
no code implementations • 19 Sep 2023 • Laura R. Marusich, Jonathan Z. Bakdash, Yan Zhou, Murat Kantarcioglu
These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.
no code implementations • 1 Jun 2023 • Kunal Mukherjee, Joshua Wiedemeier, Tianhao Wang, Muhyun Kim, Feng Chen, Murat Kantarcioglu, Kangkook Jee
PROVEXPLAINER allowed simple DT models to achieve 95% fidelity to the GNN on program classification tasks with general graph structural features, and 99% fidelity on malware detection tasks with a task-specific feature package tailored for direct interpretation.
1 code implementation • 18 May 2023 • Poupak Azad, Baris Coskunuzer, Murat Kantarcioglu, Cuneyt Gurcan Akcora
The rise of cryptocurrencies like Bitcoin, which enable transactions with a degree of pseudonymity, has led to a surge in various illicit activities, including ransomware payments and transactions on darknet markets.
no code implementations • 1 May 2023 • Joseph Bao, Murat Kantarcioglu, Yevgeniy Vorobeychik, Charles Kamhoua
Over the years, honeypots emerged as an important security tool to understand attacker intent and deceive attackers to spend time and resources.
1 code implementation • 24 Nov 2022 • Cuneyt Gurcan Akcora, Murat Kantarcioglu, Yulia R. Gel, Baris Coskunuzer
Second, we introduce a pruning algorithm for graphs to compute their persistence diagrams by removing the dominated vertices.
1 code implementation • 29 Nov 2021 • Mustafa Safa Ozdayi, Murat Kantarcioglu
Particularly, as the data distributions of agents differ, the accuracy of the trained models drop.
no code implementations • 19 Oct 2021 • Vibha Belavadi, Yan Zhou, Murat Kantarcioglu, Bhavani M. Thuraisingham
In this paper, we address the above research question by developing novel attack techniques that can simultaneously attack one set of ML models while preserving the accuracy of the other.
no code implementations • 23 Sep 2021 • Junlin Wu, Charles Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik
Next, we present a novel highly scalable approach for approximately solving such games by representing the strategies of both players as neural networks.
1 code implementation • 3 Jun 2021 • Mustafa Safa Ozdayi, Murat Kantarcioglu, Rishabh Iyer
In such a setting, we design fair training algorithms which exhibit both good utility, and low bias.
no code implementations • 10 May 2021 • Yan Zhou, Murat Kantarcioglu, Chris Clifton
We demonstrate the effectiveness of our technique on real datasets using a variety of fairness metrics.
1 code implementation • 10 Apr 2021 • Baris Coskunuzer, Cuneyt Gurcan Akcora, Ignacio Segovia Dominguez, Zhiwei Zhen, Murat Kantarcioglu, Yulia R. Gel
We derive theoretical guarantees on the stability of the new saw and multi-persistence grid functions and illustrate their applicability for graph classification tasks.
no code implementations • 1 Jan 2021 • Aref Asvadishirehjini, Murat Kantarcioglu, Bradley A. Malin
In this work, we focus on the setting where the integrity of the outsourced Deep Learning (DL) model training is ensured by TEE.
no code implementations • 17 Oct 2020 • Aref Asvadishirehjini, Murat Kantarcioglu, Bradley Malin
Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery.
no code implementations • 14 Oct 2020 • Harsh Bimal Desai, Mustafa Safa Ozdayi, Murat Kantarcioglu
It has been shown that an attacker can inject backdoors to the trained model during FL, and then can leverage the backdoor to make the model misclassify later.
no code implementations • 14 Oct 2020 • Mustafa Safa Ozdayi, Murat Kantarcioglu, Rishabh Iyer
Particularly, in settings where local data distributions vastly differ among agents, FL performs rather poorly with respect to the centralized training.
no code implementations • 22 Sep 2020 • Cuneyt G. Akcora, Sudhanva Purusotham, Yulia R. Gel, Mitchell Krawiec-Thayer, Murat Kantarcioglu
The number of blockchain users has tremendously grown in recent years.
1 code implementation • 7 Jul 2020 • Mustafa Safa Ozdayi, Murat Kantarcioglu, Yulia R. Gel
In addition, we also provide convergence rate analysis for our proposed scheme.
no code implementations • 19 Jun 2020 • Yasmeen Alufaisan, Laura R. Marusich, Jonathan Z. Bakdash, Yan Zhou, Murat Kantarcioglu
Explainable AI provides insight into the "why" for model predictions, offering potential for users to better understand and trust a model, and to recognize and correct AI predictions that are incorrect.
1 code implementation • 20 Dec 2019 • Yitao Li, Umar Islambekov, Cuneyt Akcora, Ekaterina Smirnova, Yulia R. Gel, Murat Kantarcioglu
Blockchain technology and, in particular, blockchain-based cryptocurrencies offer us information that has never been seen before in the financial world.
no code implementations • 18 Aug 2019 • Nazmiye Ceren Abay, Cuneyt Gurcan Akcora, Yulia R. Gel, Umar D. Islambekov, Murat Kantarcioglu, Yahui Tian, Bhavani Thuraisingham
With emergence of blockchain technologies and the associated cryptocurrencies, such as Bitcoin, understanding network dynamics behind Blockchain graphs has become a rapidly evolving research direction.
no code implementations • 19 Jun 2019 • Cuneyt Gurcan Akcora, Yitao Li, Yulia R. Gel, Murat Kantarcioglu
To our knowledge, none of the previous approaches have employed advanced data analytics techniques to automatically detect ransomware related transactions and malicious Bitcoin addresses.
Topological Data Analysis Cryptography and Security Distributed, Parallel, and Cluster Computing
no code implementations • 11 May 2018 • Yan Zhou, Murat Kantarcioglu, Bowei Xi
We demonstrate that introducing randomness to the DNN models is sufficient to defeat adversarial attacks, given that the adversary does not have an unlimited attack budget.
no code implementations • 13 Apr 2018 • Wutao Wei, Bowei Xi, Murat Kantarcioglu
Most of the previous work focused on adversarial classification techniques, which assumed the existence of a reasonably large amount of carefully labeled data instances.
2 code implementations • 10 Aug 2017 • Cuneyt Gurcan Akcora, Yulia R. Gel, Murat Kantarcioglu
Our goal is to provide a concise but complete description of blockchain technology that is accessible to readers with no prior expertise in the field.
Computers and Society