8 papers
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 (CNN) possible. However, the perfor…
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…
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…
HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis
Christoforos Vasilatos, Manaar Alam, Talal Rahwan +2
As the use of Large Language Models (LLMs) in text generation tasks proliferates, concerns arise over their potential to compromise academic integrity. The education sector current…
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…