7 papers
Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Sayyed Farid Ahamed, Sandip Roy, Soumya Banerjee +6
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extract…
RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks
Amit Chakraborty, Sayyed Farid Ahamed, Sandip Roy +6
Machine Learning as a Service (MLaaS) enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, the…
Retrieval Augmented Anomaly Detection (RAAD): Nimble Model Adjustment Without Retraining
Sam Pastoriza, Iman Yousfi, Christopher Redino +4
We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight…
Privacy Drift: Evolving Privacy Concerns in Incremental Learning
Sayyed Farid Ahamed, Soumya Banerjee, Sandip Roy +6
In the evolving landscape of machine learning (ML), Federated Learning (FL) presents a paradigm shift towards decentralized model training while preserving user data privacy. This…
Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning
Sayyed Farid Ahamed, Soumya Banerjee, Sandip Roy +7
Over the last few years, federated learning (FL) has emerged as a prominent method in machine learning, emphasizing privacy preservation by allowing multiple clients to collaborati…
FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks
Marc Vucovich, Devin Quinn, Kevin Choi +3
Federated learning has created a decentralized method to train a machine learning model without needing direct access to client data. The main goal of a federated learning architec…
MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
Soumya Banerjee, Sandip Roy, Sayyed Farid Ahamed +7
The membership inference attack (MIA) is a popular paradigm for compromising the privacy of a machine learning (ML) model. MIA exploits the natural inclination of ML models to over…