4 papers
Fully Decentralized Certified Unlearning
Hithem Lamri, Michail Maniatakos
Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been…
DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems
Hithem Lamri, Manaar Alam, Haiyan Jiang +1
Federated Unlearning (FU) enables clients to remove the influence of specific data from a collaboratively trained shared global model, addressing regulatory requirements such as GD…
LLMPot: Dynamically Configured LLM-based Honeypot for Industrial Protocol and Physical Process Emulation
Christoforos Vasilatos, Dunia J. Mahboobeh, Hithem Lamri +2
Industrial Control Systems (ICS) are extensively used in critical infrastructures ensuring efficient, reliable, and continuous operations. However, their increasing connectivity an…
ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
Manaar Alam, Hithem Lamri, Michail Maniatakos
Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences…