Robustness of multimodal biometric fusion methods against spoof attacks

By Ricardo Nagel Rodrigues, Lee Luan Ling, Venugopal Govindaraju. 2009

83 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Signal Processing

Citations in the corpus

Security Evaluation of Pattern Classifiers under Attack (2014, neutral): “F”
Adversarial Feature Selection Against Evasion Attacks (2016, background): “theoretical [8], [12], [20], [30] or probabilistic models of the hypothesized attack strategy [2], [9].”
Robust multimodal face and fingerprint fusion in the presence of spoofing attacks (2016, background): “Within the framework [8] adopted in this paper, liveness and recognition scores are combined considering the scenario of probe-spoofing only (i.”
Anti-spoofing in Action: Joint Operation with a Verification System (2013, background): “Most notable are [21] which explores fuzzy logic, and [20] which extends the LLR scheme by introducing hidden variables denoting the probability of a spoofing attack.”
Spoofing and countermeasures for speaker verification: A survey (2015, background): “We note, however, that Rodriques et al. (2009) and Akhtar et al. (2012) suggests it might suffice to spoof only one modality (or sub-system) under a score fusion setting in the case where the spoofing of a single, significantly weighted sub-system is particularly effective.”
Adversarial Biometric Recognition : A review on biometric system security from the adversarial machine-learning perspective (2015, background): “…if the adversary is allowed to access a restricted service or resource (e.g., an impostor gaining access to a genuine client's account [3], [9]); an availability violation , if legitimate users are denied access or normal system operation is compromised (e.g., misclassifying legitimate…”
Security evaluation of biometric authentication systems under real spoofing attacks (2012, methodology): “To this end, the following model was proposed in [29].”
Evaluation of serial and parallel multibiometric systems under spoofing attacks (2012, methodology): “However, some recent works [13, 12, 10, 3, 5, 7] have questioned the validity of this belief, and have empirically shown that spoofing only one trait is sufficient to evade a parallel multi-modal system.”
Combining match scores with liveness values in a fingerprint verification system (2012, background): “While previous research has considered the problem of designing spoof-resilient fusion schemes for multibiometric systems [20], [19], [7], [10], the specific problem of combining liveness values with match scores has not been investigated.”
Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter (2016, background): “Similarly, for approaches based on probabilistic models [16][48], the adversary can also easily construct a hard-to-predict attack instance based on cracked knowledge.”
Evaluation of biometric spoofing in a multimodal system (2010, methodology): “The Bayesian LLR was once again the most robust, but it should be remembered that this comes at the cost of lower FRR in scenario 1.”
Identifying Security Evaluation of PatternClassifiers Under attack (2015, background): “ing attack) [1], [2]; modifying network packets belonging to intrusive traffic to evade intrusion detection systems (IDSs) [3]; manipulating the content of spam emails to get them past spam filters (e.”
Biometrics Evaluation Under Spoofing Attacks (2014, methodology): “A straight-forward way to achieve this is by fusing several modes to be veriﬁed, like in [31] and [32].”