2 citations · 4 across the 9 of their papers we have counts for
13 papers
HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption
Halil İbrahim Kanpak, Sinem Sav, Alptekin Küpçü
Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these parties often hold data for the same task and wish to fine-tune…
Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks
Santhosh Parampottupadam, Andres Martinez, Dimitrios Bounias +3
Federated learning (FL) enables multi-institutional training on clinical text without sharing raw data, but gradient inversion can reconstruct sensitive information from shared mod…
HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion
Ergün Batuhan Kaynak, Kerem Bayramoglu, Sinem Sav
In this paper, we address the challenge of privacy-preserving training in federated learning (FL) by introducing a novel framework that selectively encrypts only the most privacy-s…
Bridging Local and Federated Data Normalization in Federated Learning: A Privacy-Preserving Approach
Melih Coşğun, Mert Gençtürk, Sinem Sav
Data normalization is a crucial preprocessing step for enhancing model performance and training stability. In federated learning (FL), where data remains distributed across multipl…
A Taxonomy of Attacks and Defenses in Split Learning
Aqsa Shabbir, Halil İbrahim Kanpak, Alptekin Küpçü +1
Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to serve…
Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI
Santhosh Parampottupadam, Melih Coşğun, Sarthak Pati +7
Background: Federated learning (FL) enables collaborative training of clinical AI models without centralizing patient data, but adoption is limited by privacy concerns, heterogeneo…
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
Atilla Akkus, Masoud Poorghaffar Aghdam, Mingjie Li +4
Large language models (LLMs) have demonstrated significant success in various domain-specific tasks, with their performance often improving substantially after fine-tuning. However…
CURE: Privacy-Preserving Split Learning Done Right
Halil Ibrahim Kanpak, Aqsa Shabbir, Esra Genç +2
Training deep neural networks often needs large datasets stored and processed in the cloud, and in sensitive fields like healthcare, these workflows must follow strict privacy rule…
How to Privately Tune Hyperparameters in Federated Learning? Insights from a Benchmark Study
Natalija Mitic, Apostolos Pyrgelis, Sinem Sav
In this paper, we address the problem of privacy-preserving hyperparameter (HP) tuning for cross-silo federated learning (FL). We first perform a comprehensive measurement study th…
slytHErin: An Agile Framework for Encrypted Deep Neural Network Inference
Francesco Intoci, Sinem Sav, Apostolos Pyrgelis +3
Homomorphic encryption (HE), which allows computations on encrypted data, is an enabling technology for confidential cloud computing. One notable example is privacy-preserving Pred…
Privacy-Preserving Federated Recurrent Neural Networks
Sinem Sav, Abdulrahman Diaa, Apostolos Pyrgelis +2
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relyin…
POSEIDON: Privacy-Preserving Federated Neural Network Learning
Sinem Sav, Apostolos Pyrgelis, Juan R. Troncoso-Pastoriza +4
In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an -party, federated learning setting. We propose a novel system, POSEI…
Scalable Privacy-Preserving Distributed Learning
David Froelicher, Juan R. Troncoso-Pastoriza, Apostolos Pyrgelis +4
In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstracti…