Multimodal fusion vulnerability to non-zero effort (spoof) imposters

By Peter A. Johnson, Bozhao Tan, Stephanie A. C. Schuckers. 2010

87 citations recorded by the source corpus.

Subfields: Information Systems, Psychiatry and Mental health, Social Psychology, Multimodal Learning, Safety, Robustness & Interpretability

How researchers see this paper

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

In Information Systems

In Psychiatry and Mental health

In Social Psychology

In Multimodal Learning

In Safety, Robustness & Interpretability

Citations in the corpus

Security Evaluation of Pattern Classifiers under Attack (2014, neutral): “F”
Robust multimodal face and fingerprint fusion in the presence of spoofing attacks (2016, background): “accepted), rather than False Acceptance Rate (FAR) and GAR pairs, see [36].”
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.”
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.”
Robustness of multi-modal biometric verification systems under realistic spoofing attacks (2011, methodology): “Note that, in the evaluation of spoofing attacks, the FAR corresponds to the percentage of spoofing attempts that were accepted as genuine (the term SFAR was used to this aim in [13]).”
Evaluation of multimodal biometric score fusion rules under spoof attacks (2012, background): “Previous works in the literature [3, 4] have avoided the problem of fabricating fake samples by assuming a “worst-case” scenario, where the attacker is able to exactly replicate the genuine user’s trait.”
A Survey on Anti-Spooﬁng Schemes for Fingerprint Recognition Systems (2014, background): “The vulnerability of multimodal biometric systems to partial spoof attacks was also explored by Johnson et al. in [Johnson et al. 2010].”
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.”
Towards anomaly detection for increased security in multibiometric systems: Spoofing-resistant 1-median fusion eliminating outliers (2014, background): “1) showing the relationship between Genuine Acceptance Rate (GAR, the percentage of genuine users being accepted) and False Acceptance Rate (FAR, percentage of impostors being accepted) for m = 0, and Spoof False Acceptance Rate (SFAR, percentage of spoof-attempts being accepted) as introduced in [6”
Adversarial Biometric Recognition : A review on biometric system security from the adversarial machine-learning perspective (2015, background): “extractor : Z X 7 z to obtain a compact representation x X !”