Search Results - "Ozdayi, Mustafa"

Leveraging blockchain for immutable logging and querying across multiple sites by Ozdayi, Mustafa Safa, Kantarcioglu, Murat, Malin, Bradley

“…Blockchain has emerged as a decentralized and distributed framework that enables tamper-resilience and, thus, practical immutability for stored data. This…”
Get full text

The Impact of Data Distribution on Fairness and Robustness in Federated Learning by Ozdayi, Mustafa Safa, Kantarcioglu, Murat

“…Federated Learning (FL) is a distributed machine learning protocol that allows a set of agents to collaboratively train a model without sharing their datasets…”
Get full text

The Impact of Data Distribution on Fairness and Robustness in Federated Learning by Ozdayi, Mustafa Safa, Kantarcioglu, Murat

“…Federated Learning (FL) is a distributed machine learning protocol that allows a set of agents to collaboratively train a model without sharing their datasets…”
Get full text

Achieving Competitiveness in Online Problems by Ozdayi, Mustafa Safa

“…In the setting of online algorithms, the input is initially not present but rather arrive one-by-one over time and after each input, the algorithm has to make…”
Get full text

Fair Machine Learning under Limited Demographically Labeled Data by Ozdayi, Mustafa Safa, Kantarcioglu, Murat, Iyer, Rishabh

“…Research has shown that, machine learning models might inherit and propagate undesired social biases encoded in the data. To address this problem, fair…”
Get full text

Improving Accuracy of Federated Learning in Non-IID Settings by Ozdayi, Mustafa Safa, Kantarcioglu, Murat, Iyer, Rishabh

“…Federated Learning (FL) is a decentralized machine learning protocol that allows a set of participating agents to collaboratively train a model without sharing…”
Get full text

Generating massive complex networks with hyperbolic geometry faster in practice by von Looz, Moritz, Ozdayi, Mustafa Safa, Laue, Soren, Meyerhenke, Henning

“…Generative network models play an important role in algorithm development, scaling studies, network analysis, and realistic system benchmarks for graph data…”
Get full text

Secure IoT Data Analytics in Cloud via Intel SGX by Islam, Md Shihabul, Ozdayi, Mustafa Safa, Khan, Latifur, Kantarcioglu, Murat

“…The growing adoption of IoT devices in our daily life is engendering a data deluge, mostly private information that needs careful maintenance and secure…”
Get full text

Leveraging Blockchain for Immutable Logging and Querying Across Multiple Sites by Ozdayi, Mustafa Safa, Kantarcioglu, Murat, Malin, Bradley

“…Blockchain has emerged as a decentralized and distributed framework that enables tamper-resilience and, thus, practical immutability for stored data. This…”
Get full text

Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning by Ozdayi, Mustafa Safa, Peris, Charith, FitzGerald, Jack, Dupuy, Christophe, Majmudar, Jimit, Khan, Haidar, Parikh, Rahil, Gupta, Rahul

“…Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be…”
Get full text

BlockFLA: Accountable Federated Learning via Hybrid Blockchain Architecture by Desai, Harsh Bimal, Ozdayi, Mustafa Safa, Kantarcioglu, Murat

“…Federated Learning (FL) is a distributed, and decentralized machine learning protocol. By executing FL, a set of agents can jointly train a model without…”
Get full text

Secure IoT Data Analytics in Cloud via Intel SGX by Islam, Md Shihabul, Ozdayi, Mustafa Safa, Khan, Latifur, Kantarcioglu, Murat

“…The growing adoption of IoT devices in our daily life is engendering a data deluge, mostly private information that needs careful maintenance and secure…”
Get full text

Defending against Backdoors in Federated Learning with Robust Learning Rate by Ozdayi, Mustafa Safa, Kantarcioglu, Murat, Gel, Yulia R

“…Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for…”
Get full text

Towards a Two-Tier Hierarchical Infrastructure: An Offline Payment System for Central Bank Digital Currencies by Christodorescu, Mihai, Gu, Wanyun Catherine, Kumaresan, Ranjit, Minaei, Mohsen, Ozdayi, Mustafa, Price, Benjamin, Raghuraman, Srinivasan, Saad, Muhammad, Sheffield, Cuy, Xu, Minghua, Zamani, Mahdi

“…Digital payments traditionally rely on online communications with several intermediaries such as banks, payment networks, and payment processors in order to…”
Get full text

Generating massive complex networks with hyperbolic geometry faster in practice by von Looz, Moritz, Özdayi, Mustafa, Laue, Sören, Meyerhenke, Henning

“…Generative network models play an important role in algorithm development, scaling studies, network analysis, and realistic system benchmarks for graph data…”
Get full text