Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies

Document Type

Conference Proceeding

Source of Publication

Smart Innovation Systems and Technologies

Publication Date

1-1-2026

Abstract

With the rise in the wholesale adoption of Deep Learning (DL) models in nearly all aspects of society, a unique set of challenges is imposed. Primarily centered around the architectures of these models, these risks pose a significant challenge, and addressing these challenges is key to their successful implementation and usage in future. In this research, we present the security challenges associated with the current DL models deployed into production, as well as anticipate the challenges of future DL technologies based on the advancements in computing, AI, and hardware technologies. In addition, we propose risk mitigation techniques to inhibit these challenges and provide metrical evaluations to measure the effectiveness of these metrics.

ISBN

[9789819668588]

ISSN

2190-3018

Publisher

Springer Nature Singapore

Volume

119 SIST

First Page

185

Last Page

194

Disciplines

Computer Sciences

Keywords

Explainability, Interpretability, Model vulnerability, Security of Deep Learning

Scopus ID

105028313423

Indexed in Scopus

yes

Open Access

no

Share

COinS