Demographic Bias in Biometrics: A Survey on an Emerging Challenge

Drozdowski, Pawel; Rathgeb, Christian; Dantcheva, Antitza; Damer, Naser; Busch, Christoph

doi:10.1109/tts.2020.2992344

Cited by 184 publications

(132 citation statements)

References 108 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…Despite the high performance of face recognition, it is still prone to certain vulnerabilities towards operation scenarios and attacks. Examples of these vulnerabilities are presentation attack detection (spoofing) [6], [37], face morphing attacks [7], [8], and the inherited differential performance (bias between different demographic groups) [12], [50]. As this work focus on the privacy aspect of face recognition, the discussed related work will go deeper into this issue.…”

Section: Related Workmentioning

confidence: 99%

PE-MIU: A Training-Free Privacy-Enhancing Face Recognition Approach Based on Minimum Information Units

et al. 2020

Self Cite

View full text Add to dashboard Cite

Research on soft-biometrics showed that privacy-sensitive information can be deduced from biometric data. Utilizing biometric templates only, information about a persons gender, age, ethnicity, sexual orientation, and health state can be deduced. For many applications, these templates are expected to be used for recognition purposes only. Thus, extracting this information raises major privacy issues. Previous work proposed two kinds of learning-based solutions for this problem. The first ones provide strong privacy-enhancements, but limited to pre-defined attributes. The second ones achieve more comprehensive but weaker privacy-improvements. In this work, we propose a Privacy-Enhancing face recognition approach based on Minimum Information Units (PE-MIU). PE-MIU, as we demonstrate in this work, is a privacy-enhancement approach for face recognition templates that achieves strong privacy-improvements and is not limited to pre-defined attributes. We exploit the structural differences between face recognition and facial attribute estimation by creating templates in a mixed representation of minimal information units. These representations contain pattern of privacy-sensitive attributes in a highly randomized form. Therefore, the estimation of these attributes becomes hard for function creep attacks. During verification, these units of a probe template are assigned to the units of a reference template by solving an optimal best-matching problem. This allows our approach to maintain a high recognition ability. The experiments are conducted on three publicly available datasets and with five state-of-the-art approaches. Moreover, we conduct the experiments simulating an attacker that knows and adapts to the systems privacy mechanism. The experiments demonstrate that PE-MIU is able to suppress privacy-sensitive information to a significantly higher degree than previous work in all investigated scenarios. At the same time, our solution is able to achieve a verification performance close to that of the unmodified recognition system. Unlike previous works, our approach offers a strong and comprehensive privacy-enhancement without the need of training.

show abstract

Section: Related Workmentioning

confidence: 99%

PE-MIU: A Training-Free Privacy-Enhancing Face Recognition Approach Based on Minimum Information Units

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…a camera or microphone, a database that stores information about the persons registered in the biometrics system, algorithms for processing the acquired characteristics, e.g. signal processing algorithms, and finally a decision system that compares the stored and the captured characteristics and decides whether they belong to the same person [2]. Success in the comparison of the biometrics trait grants access to a system or identifies an individual.…”

Section: Introductionmentioning

confidence: 99%

BED: A New Data Set for EEG-Based Biometrics

Arnau-González

Katsigiannis

Arevalillo‐Herráez

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Professional screeners need to maintain safety by identifying such imposters, while still allowing lawful passengers through. Although technological advancements such as automatic face recognition systems (e.g., Taigman et al, 2014 ) and various methods of biometric scanning may seem like attractive alternatives to replace human screeners, such technologies face many of the same challenges as human recognizers (O’Toole et al, 2012 ; e.g., Tran et al, 2017 ), while also raising concerns about ethics, transparency, and accountability (Drozdowski et al, 2020 ). Therefore, the bulk of imposter detection duties has been and is being performed by humans.…”

Section: Introductionmentioning

confidence: 99%

When experience does not promote expertise: security professionals fail to detect low prevalence fake IDs

2021

View full text Add to dashboard Cite

Professional screeners frequently verify photograph IDs in such industries as professional security, bar tending, and sales of age-restricted materials. Moreover, security screening is a vital tool for law enforcement in the search for missing or wanted persons. Nevertheless, previous research demonstrates that novice participants fail to spot fake IDs when they are rare (i.e., the low prevalence effect; LPE). To address whether this phenomenon also occurs with professional screeners, we conducted three experiments. Experiment 1 compared security professional and non-professionals. Experiment 2 compared bar-security professionals, access-security professionals, and non-professionals. Finally, Experiment 3 added a newly created Professional Identity Training Questionnaire to determine whether and how aspects of professionals’ employment predict ID-matching accuracy. Across all three experiments, all participants were susceptible to the LPE regardless of professional status. Neither length/type of professional experience nor length/type of training experience affected ID verification performance. We discuss task performance and survey responses with aims to acknowledge and address this potential problem in real-world screening scenarios.

show abstract

Demographic Bias in Biometrics: A Survey on an Emerging Challenge

Cited by 184 publications

References 108 publications

PE-MIU: A Training-Free Privacy-Enhancing Face Recognition Approach Based on Minimum Information Units

PE-MIU: A Training-Free Privacy-Enhancing Face Recognition Approach Based on Minimum Information Units

BED: A New Data Set for EEG-Based Biometrics

When experience does not promote expertise: security professionals fail to detect low prevalence fake IDs

Contact Info

Product

Resources

About