Secure Gait Recognition-Based Smart Surveillance Systems Against Universal Adversarial Attacks

Secure Gait Recognition-Based Smart Surveillance Systems Against Universal Adversarial Attacks

Maryam Bukhari, Sadaf Yasmin, Saira Gillani, Muazzam Maqsood, Seungmin Rho, Sang Soo Yeo
Copyright: © 2023 |Pages: 25
DOI: 10.4018/JDM.318415
Article PDF Download
Open access articles are freely available for download

Abstract

Currently, the internet of everything (IoE) enabled smart surveillance systems are widely used in various fields to prevent various forms of abnormal behaviors. The authors assess the vulnerability of surveillance systems based on human gait and suggest a defense strategy to secure them. Human gait recognition is a promising biometric technology, but one significantly hindered because of universal adversarial perturbation (UAP) that may trigger system failure. More specifically, in this research study, the authors emphasize on sample convolutional neural network (CNN) model design for gait recognition and assess its susceptibility to UAPs. The authors compute the perturbation as non-targeted UAPs, which trigger a model failure and lead to an inaccurate label to the input sample of a given subject. The findings show that a smart surveillance system based on human gait analysis is susceptible to UAPs, even if the norm of the generated noise is substantially less than the average norm of the images. Later, in the next stage, the authors illustrate a defense mechanism to design a secure surveillance system based on human gait.
Article Preview
Top

1. Introduction

The Internet of Everything (IoE) is a phrase in information technology that evolved from the internet of things (IoT) as time has progressed (Kubba & Hoomod, 2019). IoE links numerous items and things over the internet using embedded sensors to gather and analyze data in an intelligent manner (Thabit, Mahmoud, Alkhayyat, & Abbasi, 2019). More specifically, it can gather and interpret real-time data from a multitude of sensors, like as cameras that are linked to it (Miraz, Ali, Excell, & Picking, 2015). As a result, automated systems based on IoE innovation have major features such as real-time computing, detecting, updating, regulating, and observing. Currently, the IoE has emerging applications in several domains such as the healthcare industry(Mardini, Aljawarneh, & Al-Abdi, 2021), surveillance (Maitra, Giri, & Sarkar, 2021), agriculture (Mohapatra & Rath, 2022), and many more. Because of all these extensive capabilities, the IoE-enabled smart surveillance system is a fascinating emerging technology. In such a system, surveillance can be accomplished using various ways, however, human gait-based surveillance is in high demand because of their excellent qualities that make more effective video surveillance systems (Angadi & Nandyal, 2020). In previous years, human identification through gait becomes a very popular area of research. Gait is a kind of behavioral biometric in which a person’s manner of walking is considered to identify them.

It can be considered as a next-generation approach to biometric systems due to its wide applications in surveillance systems (Alsaggaf et al., 2021; Ran, Zheng, Chellappa, & Strat, 2010). Gait recognition methods are broadly divided into two main groups which are model-based and appearance-based or model-free approaches (BenAbdelkader, Cutler, & Davis, 2002; Yang, Larsen, Alkjær, Simonsen, & Lynnerup, 2014). Moreover, CNNs are the most commonly used algorithm in appearance-based methods with remarkable performances (Alotaibi & Mahmood, 2017; Hawas, El-Khobby, Abd-Elnaby, & Abd El-Samie, 2019; Linda, Themozhi, & Bandi, 2020). Usually, in appearance-based methods, Gait Energy Image(GEI)(Han & Bhanu, 2005) is the most commonly used gait representation.

Complete Article List

Search this Journal:
Reset
Volume 35: 1 Issue (2024)
Volume 34: 3 Issues (2023)
Volume 33: 5 Issues (2022): 4 Released, 1 Forthcoming
Volume 32: 4 Issues (2021)
Volume 31: 4 Issues (2020)
Volume 30: 4 Issues (2019)
Volume 29: 4 Issues (2018)
Volume 28: 4 Issues (2017)
Volume 27: 4 Issues (2016)
Volume 26: 4 Issues (2015)
Volume 25: 4 Issues (2014)
Volume 24: 4 Issues (2013)
Volume 23: 4 Issues (2012)
Volume 22: 4 Issues (2011)
Volume 21: 4 Issues (2010)
Volume 20: 4 Issues (2009)
Volume 19: 4 Issues (2008)
Volume 18: 4 Issues (2007)
Volume 17: 4 Issues (2006)
Volume 16: 4 Issues (2005)
Volume 15: 4 Issues (2004)
Volume 14: 4 Issues (2003)
Volume 13: 4 Issues (2002)
Volume 12: 4 Issues (2001)
Volume 11: 4 Issues (2000)
Volume 10: 4 Issues (1999)
Volume 9: 4 Issues (1998)
Volume 8: 4 Issues (1997)
Volume 7: 4 Issues (1996)
Volume 6: 4 Issues (1995)
Volume 5: 4 Issues (1994)
Volume 4: 4 Issues (1993)
Volume 3: 4 Issues (1992)
Volume 2: 4 Issues (1991)
Volume 1: 2 Issues (1990)
View Complete Journal Contents Listing