activity
20182026
most citedPerception, performance, and detectability of conversational artificial intelligence across 32 university courses

151 citations · 253 across the 29 of their papers we have counts for

collaborators
Showing 2025Show all

6 papers · 1 filter

cs.LG2025

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…

cs.LG2025

BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity

Alejandro Guerra-Manzanares, Omar El-Herraoui, Michail Maniatakos +1

One of the key challenges of collaborative machine learning, without data sharing, is multimodal data heterogeneity in real-world settings. While Federated Learning (FL) enables mo…

cs.CR2025

PAPER: Privacy-Preserving Convolutional Neural Networks using Low-Degree Polynomial Approximations and Structural Optimizations on Leveled FHE

Eduardo Chielle, Manaar Alam, Jinting Liu +2

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNNs) possible. However, the perfo…

cs.LG2025

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…

cs.AR2025★ 1 cited

Veritas: Deterministic Verilog Code Synthesis from LLM-Generated Conjunctive Normal Form

Prithwish Basu Roy, Akashdeep Saha, Manaar Alam +4

Automated Verilog code synthesis poses significant challenges and typically demands expert oversight. Traditional high-level synthesis (HLS) methods often fail to scale for real-wo…

cs.CR2025

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…