Search Results for author: Manaar Alam

Found 9 papers, 0 papers with code

HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis

no code implementations26 May 2023 Christoforos Vasilatos, Manaar Alam, Talal Rahwan, Yasir Zaki, Michail Maniatakos

As the use of Large Language Models (LLMs) in text generation tasks proliferates, concerns arise over their potential to compromise academic integrity.

Specificity Text Generation

Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning

no code implementations20 Apr 2023 Manaar Alam, Hithem Lamri, Michail Maniatakos

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data.

Federated Learning Image Classification +1

Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundaries

no code implementations18 Aug 2022 Manaar Alam, Shubhajit Datta, Debdeep Mukhopadhyay, Arijit Mondal, Partha Pratim Chakrabarti

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks.

Image Classification

On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel

no code implementations1 Aug 2022 Shubhi Shukla, Manaar Alam, Sarani Bhattacharya, Debdeep Mukhopadhyay, Pabitra Mitra

In this paper, as a separate case study, we demonstrate that a DL model secured with differential privacy (a popular countermeasure against MIA) is still vulnerable to MIA against an adversary exploiting Class Leakage.

Benchmarking Image Classification +2

PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks via Pairwise Adversarially Robust Loss Function

no code implementations9 Dec 2021 Manaar Alam, Shubhajit Datta, Debdeep Mukhopadhyay, Arijit Mondal, Partha Pratim Chakrabarti

Ensemble methods against adversarial attacks demonstrate that an adversarial example is less likely to mislead multiple classifiers in an ensemble having diverse decision boundaries.

Image Classification

Deep-Lock: Secure Authorization for Deep Neural Networks

no code implementations13 Aug 2020 Manaar Alam, Sayandeep Saha, Debdeep Mukhopadhyay, Sandip Kundu

Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models.

Scheduling

How Secure are Deep Learning Algorithms from Side-Channel based Reverse Engineering?

no code implementations13 Nov 2018 Manaar Alam, Debdeep Mukhopadhyay

Deep Learning algorithms have recently become the de-facto paradigm for various prediction problems, which include many privacy-preserving applications like online medical image analysis.

Privacy Preserving Two-sample testing

Adversarial Attacks and Defences: A Survey

no code implementations28 Sep 2018 Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, Debdeep Mukhopadhyay

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past.

Cannot find the paper you are looking for? You can Submit a new open access paper.