Search Results for author: Michail Maniatakos

Found 12 papers, 1 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

Privacy-preserving machine learning for healthcare: open challenges and future perspectives

no code implementations27 Mar 2023 Alejandro Guerra-Manzanares, L. Julian Lechuga Lopez, Michail Maniatakos, Farah E. Shamout

Machine Learning (ML) has recently shown tremendous success in modeling various healthcare prediction tasks, ranging from disease diagnosis and prognosis to patient treatment.

Privacy Preserving

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

no code implementations24 Mar 2023 Yue Wang, Wending Li, Michail Maniatakos, Saif Eddin Jabari

The effectiveness of the proposed method is verified on a simulated traffic system based on a microscopic traffic simulator, where experimental results showcase that the smoothed traffic controller can neutralize all trigger samples and maintain the performance of relieving traffic congestion

Autonomous Vehicles Image Classification

Scalable privacy-preserving cancer type prediction with homomorphic encryption

no code implementations12 Apr 2022 Esha Sarkar, Eduardo Chielle, Gamze Gursoy, Leo Chen, Mark Gerstein, Michail Maniatakos

Privacy concerns in outsourced ML, especially in the field of genetics, motivate the use of encrypted computation, like Homomorphic Encryption (HE).

Decision Making feature selection +3

PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

no code implementations17 Mar 2022 Yue Wang, Wenqing Li, Esha Sarkar, Muhammad Shafique, Michail Maniatakos, Saif Eddin Jabari

Based on our theoretical analysis and experimental results, we demonstrate the effectiveness of PiDAn in defending against backdoor attacks that use different settings of poisoned samples on GTSRB and ILSVRC2012 datasets.

Anomaly Detection Backdoor Attack

ICSML: Industrial Control Systems ML Framework for native inference using IEC 61131-3 code

1 code implementation21 Feb 2022 Constantine Doumanidis, Prashant Hari Narayan Rajput, Michail Maniatakos

This has inspired defense research that focuses heavily on Machine Learning (ML) based anomaly detection methods that run on external IT hardware, which means an increase in costs and the further expansion of the threat landscape.

Anomaly Detection

TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis

no code implementations14 Aug 2021 Esha Sarkar, Michail Maniatakos

Using a real-world cancer dataset, we analyze the dataset with the bias that already existed towards white individuals and also introduced biases in datasets artificially, and our experimental result show that TRAPDOOR can detect the presence of dataset bias with 100% accuracy, and furthermore can also extract the extent of bias by recovering the percentage with a small error.

BIG-bench Machine Learning

Explainability Matters: Backdoor Attacks on Medical Imaging

no code implementations30 Dec 2020 Munachiso Nwadike, Takumi Miyawaki, Esha Sarkar, Michail Maniatakos, Farah Shamout

Extensive evaluation of a state-of-the-art architecture demonstrates that by introducing images with few-pixel perturbations into the training set, an attacker can execute the backdoor successfully without having to be involved with the training procedure.

FaceHack: Triggering backdoored facial recognition systems using facial characteristics

no code implementations20 Jun 2020 Esha Sarkar, Hadjer Benkraouda, Michail Maniatakos

In this work, we demonstrate that specific changes to facial characteristics may also be used to trigger malicious behavior in an ML model.

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