The magic passport

Ferrara, Matteo; Franco, Annalisa; Maltoni, Davide

doi:10.1109/btas.2014.6996240

Cited by 229 publications

(218 citation statements)

References 2 publications

Supporting

Mentioning

197

Contrasting

Unclassified

Order By: Relevance

“…If we perform identification tasks with state of the art facial recognition software, a good morph will generate high scores for comparisons between morph M and templates of subjects A and B. It is obvious that face morphing poses a severe threat to all processes where face recognition is used to establish the identity of subjects, as first reported in [1]. Also human face recognition is vulnerable, as reported by Robertson et al [2].…”

Section: Introductionmentioning

confidence: 94%

Towards Robust Evaluation of Face Morphing Detection

Spreeuwers

Schils

Veldhuis

2018

2018 26th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Automated face recognition is increasingly used as a reliable means to establish the identity of persons for various purposes, ranging from automated passport checks at the border to transferring money and unlocking mobile phones. Face morphing is a technique to blend facial images of two or more subjects such that the result resembles both subjects. Face morphing attacks pose a serious risk for any face recognition system. Without automated morphing detection, state of the art face recognition systems are extremely vulnerable to morphing attacks. Morphing detection methods published in literature often only work for a few types of morphs or on a single dataset with morphed photographs. We create face morphing databases with varying characteristics and how for a LBP/SVM based morphing detection method that performs on par with the state of the art (around 2% EER), the performance collapses with an EER as high as if it is tested across databases with different characteristics. In addition we show that simple image manipulations like adding noise or rescaling can be used to obscure morphing artifacts and deteriorate the morphing detection performance.

show abstract

Section: Introductionmentioning

confidence: 94%

Towards Robust Evaluation of Face Morphing Detection

Spreeuwers

Schils

Veldhuis

2018

2018 26th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

Section: Executive Summary Backgroundmentioning

confidence: 99%

“…If a morphed photo gets onto an identity credential for example, multiple, if not all constituents of the morph, can use the same identity credential. Morphs can be used to fool both humans [1] [2] and current face recognition systems [3], which presents a vulnerability to current identity verification processes. Figure 1 illustrates the impact of morphed photos on current algorithms from some of the leading face recognition algorithms (labeled as A, B, C, and D) submitted to the NIST Ongoing FRVT 1:1 Verification test.…”

Section: The Frvt Morph Activitymentioning

confidence: 99%

“…For each dataset, Failure to Process (Morphs) is the proportion of morphed photos the software fails on; Failure to Process (Bona Fides) q is the proportion of source images used as bona fides the software fails to process; and Failure to Process (Bona Fides) m is the proportion of mugshot photos used as bona fides the software fails to process. ntnussl-002 Online tool from website 1.00 0.00 -0.00 0.00 -0.00 0.64 0.99 (1) hdalbp-005 Online tool from website 0.80 0.14 0.56 0.18 0.01 0.02 0.17 0.91 1.00 (2) hdabsif-004 Online tool from website 0.04 0.98 0.00 0.71 0.00 0.00 0.01 0.98 1.00 (3) hdaprnu-002 Online tool from website 0.10 0.96 0.99 0.89 0.00 0.04 0.29 0.98 1.00 (4) hdalbp-006 Online tool from website 0.77 0.42 0.79 0.41 0.00 0.00 0.01 0.99 1.00 (5) unibo-000 Online tool from website 0.99 0.07 0.01 0.09 0.00 0.00 0.00 0.99 1.00 (6) hdaprnu-004 Online tool from website 0.94 0.33 0.69 0.30 0.00 0.00 0.01 1.00 1.00 (7) ntnussl-001 Online tool from website 0.38 0.28 --0.00 ---- (1) unibo-000 Global Morph 0.80 0.01 0.01 0.09 0.00 0.00 0.00 0.76 1.00 (2) ntnussl-002 Global Morph 1.00 0.00 -0.00 0.00 -0.00 0.78 1.00 (3) hdalbp-006 Global Morph 0.46 0.11 0.79 0.41 0.00 0.00 0.01 0.98 1.00 (4) hdabsif-004 Global Morph 0.05 0.84 0.00 0.71 0.00 0.00 0.01 1.00 1.00 (5) hdaprnu-002 Global Morph 0.19 0.48 0.99 0.89 0.03 0.04 0.29 1.00 1.00 (6) APCER: This is the rate that morphs that are not detected. Lower values are better.…”

Section: Failure To Processmentioning

confidence: 99%

See 1 more Smart Citation

Face Recognition Vendor Test (FRVT) part 4:

Ngan¹,

Grother²,

Hanaoka³

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In other words, the subjects whose biometric samples were used to create the morphed image can both be matched (accepted) during subsequent biometric recognition transactions with the morphed reference image. This vulnerability was first introduced by Ferrara et al [12] (the so-called "magic passport") and shown to be a feasible attack vector against automated systems and human experts alike [13]. A typical morphing process includes:…”

Section: Morphing Of Facial Imagesmentioning

confidence: 99%

Turning a Vulnerability into an Asset: Accelerating Facial Identification with Morphing

Drozdowski

Rathgeb

Busch

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In recent years, morphing of facial images has arisen as an important attack vector on biometric systems. Detection of morphed images has proven challenging for automated systems and human experts alike. Likewise, in recent years, the importance of efficient (fast) biometric identification has been emphasised by the rapid rise and growth of large-scale biometric systems around the world. In this paper, the aforementioned, hitherto unrelated, topics within the biometrics domain are combined: the properties of morphed images are exploited for the purpose of improving the transaction times of a biometric identification system. Specifically, morphs of two or more samples are used in the pre-selection step of a two-stage biometric identification system. In a proof-of-concept experimental evaluation using two state-of-the-art open-source facial recognition frameworks it is shown, that the proposed system achieves hit rates comparable to that of an exhaustive search-based baseline, while significantly reducing the penetration rate (and thus the computational workload) associated with the biometric identification transactions.

show abstract

The magic passport

Cited by 229 publications

References 2 publications

Towards Robust Evaluation of Face Morphing Detection

Towards Robust Evaluation of Face Morphing Detection

Face Recognition Vendor Test (FRVT) part 4:

Turning a Vulnerability into an Asset: Accelerating Facial Identification with Morphing

Contact Info

Product

Resources

About