Backdoor Breakthrough: Unveiling Next-Gen Clustering Defenses for NLP Model Integrity

View Sample PDF

Author(s): Angel Justo Jones (Capitol Technology University, USA & University of Virginia, USA)
Copyright: 2024
Pages: 17
Source title: Innovations, Securities, and Case Studies Across Healthcare, Business, and Technology
Source Author(s)/Editor(s): Darrell Norman Burrell (Marymount University, USA)
DOI: 10.4018/979-8-3693-1906-2.ch008

Keywords: Medical Information Science Reference / Medical Technologies / Medicine & Healthcare

Purchase

View Backdoor Breakthrough: Unveiling Next-Gen Clustering Defenses for NLP Model Integrity on the publisher's website for pricing and purchasing information.

Abstract

This study introduces “NeuroGuard,” an innovative defense mechanism designed to enhance the security of natural language processing (NLP) models against complex backdoor attacks. Diverging from traditional methodologies, NeuroGuard employs a sophisticated variant of the k-means clustering algorithm, meticulously crafted to detect and neutralize hidden backdoor triggers in data. This novel approach is universally adaptable, providing a robust safeguard across a wide range of NLP applications without sacrificing performance. Through rigorous experimentation and in-depth comparative analysis, NeuroGuard outperforms existing defense strategies, significantly reducing the effectiveness of backdoor attacks. This breakthrough in NLP model security represents a crucial step forward in protecting the integrity of language-based AI systems.

The IRMA Community

Research IRM

Backdoor Breakthrough: Unveiling Next-Gen Clustering Defenses for NLP Model Integrity

Purchase

Abstract

Related Content

IRMA Sponsors