Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.082713
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

HEbdMIA: Lightweight Logit Encryption for Membership Inference Defense

Akash Shah1, Mudasir Ahmad Wani2,*, Ravi Prakash Chaturvedi3, Shri Kant3, Nidhi Sindhwani1, Kashish Ara Shakil4, Sulieman Alshuhri2
1 Amity Institute of Information Technology, Amity University, Noida, Uttar Pradesh, India
2 College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia
3 Center for Cyber Security and Cryptology, School of Computing Science and Engineering, Sharda University, Greater Noida, Uttar Pradesh, India
4 Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia
* Corresponding Author: Mudasir Ahmad Wani. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.082713

Received 21 March 2026; Accepted 13 May 2026; Published online 08 July 2026

Abstract

Membership Inference Attacks (MIAs) pose a significant privacy risk in machine learning by enabling adversaries to infer whether specific data samples were used during training, particularly in sensitive domains such as social media and mental health analytics. To address this challenge, this paper proposes HEbdMIA, a lightweight homomorphic encryption-based defense that operates at the post-inference stage by encrypting model output logits without requiring retraining or architectural modifications. The proposed approach preserves the relative ordering of predictions while obscuring confidence patterns exploited by MIAs. Experimental evaluation on DepInferAttack and BotInferAttack demonstrates that HEbdMIA achieves a reduction in MIA success rates of 31.0% and 27.3%, respectively, with an associated accuracy decrease of 29.3% and 26.4%, reflecting a controlled privacy and utility trade off. Additional analysis using precision, recall, F1-score, and ROC-AUC confirms a substantial decline in adversarial inference capability. These findings indicate that HEbdMIA provides an effective, scalable, and deployment-friendly solution for enhancing privacy in real-world machine learning systems.

Keywords

Membership inference attack; homomorphic encryption; machine learning; encrypted data; logit encryption; model security

  • 159

    View

  • 39

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link