Abstract:Biometrics is an emerging technology more and more present in our daily life. However, building biometric systems requires a large amount of data that may be difficult to collect. Collecting such sensitive data is also very time consuming and constrained, s.a. GDPR legislation in Europe. In the case of keystroke dynamics, most existing databases have less than 200 users. For these reasons, it is crucial for this biometric modality to be able to generate a significant and realistic synthetic dataset of keystrok… Show more
“…There is no pressure to collect several samples for enrollment as the network has been trained with other individuals samples and expect that few samples allow obtaining good performances with an increase of performance with the number of samples. To verify this point, we try different gallery size: [1,5,10,20,30,40,50,100,150,200]. We expect to obtain good performance even for few samples.…”
Section: E Evaluation Of the Proposed Methodsmentioning
confidence: 98%
“…A generalization to a user-based password authentication [7] or even free text is expected. Artificial samples generation with handcrafted methods [9], [20] or Generative Adversarial Networks [21] could help to generate additional training data if required for such system.…”
Section: Limitations Of the Proposed Methodsmentioning
Keystroke dynamics authentication aims at recognizing individuals on their way of typing on a keyboard. It suffers from a high intra-class variability as any behavioral biometric modality; to provide a large quantity of enrollment samples often overcomes this issue.In this paper, we analyze the feasibility of using siamese networks to rely on biometric samples provided by other users instead of requesting a new user to provide a large number of enrollment samples. Such networks aim at comparing two inputs to compute their similarity: the authentication process consists then at comparing the query to an enrollment sample.The proposed method is compared to several compatible baselines in the literature. Its EER outperforms the best baseline of 28% in a oneshot context and 31% when using 200 enrollment samples. This proves the viability of such approach and opens the path to improvements for using it in other contexts of keystroke dynamics authentication.
“…There is no pressure to collect several samples for enrollment as the network has been trained with other individuals samples and expect that few samples allow obtaining good performances with an increase of performance with the number of samples. To verify this point, we try different gallery size: [1,5,10,20,30,40,50,100,150,200]. We expect to obtain good performance even for few samples.…”
Section: E Evaluation Of the Proposed Methodsmentioning
confidence: 98%
“…A generalization to a user-based password authentication [7] or even free text is expected. Artificial samples generation with handcrafted methods [9], [20] or Generative Adversarial Networks [21] could help to generate additional training data if required for such system.…”
Section: Limitations Of the Proposed Methodsmentioning
Keystroke dynamics authentication aims at recognizing individuals on their way of typing on a keyboard. It suffers from a high intra-class variability as any behavioral biometric modality; to provide a large quantity of enrollment samples often overcomes this issue.In this paper, we analyze the feasibility of using siamese networks to rely on biometric samples provided by other users instead of requesting a new user to provide a large number of enrollment samples. Such networks aim at comparing two inputs to compute their similarity: the authentication process consists then at comparing the query to an enrollment sample.The proposed method is compared to several compatible baselines in the literature. Its EER outperforms the best baseline of 28% in a oneshot context and 31% when using 200 enrollment samples. This proves the viability of such approach and opens the path to improvements for using it in other contexts of keystroke dynamics authentication.
“…Fixed-text Keystroke Dynamics datasets used in this study are described in Table 1. As described in [5,6], these datasets have been cleaned and only the first 45 entries of each user are kept. Metrics given in this paper are computed as the average value of the metric across the 4 datasets.…”
Section: Keystroke Dynamics Datasetsmentioning
confidence: 99%
“…However, such representation (raw) gives disappointing performances (EER=40%). As stated in [5], 6 duration times can be extracted from each digraph, with the last duration of a given digraph (d 5 ) also being the first duration (d 0 ) of the next digraph. However, as these duration times can be rewritten as additions of dwell and flight times, they are, by construction, not bringing any additional security or performance to the BioHashing algorithm.…”
Section: Fixed-text Keystroke Dynamicsmentioning
confidence: 99%
“…A more practical estimation of cdf i (X i ) is to compute the parameters of the law X i is assumed to follow. In this study, we used the same laws (gumbel, normal, logistic, and laplace) and fitness functions (raw, R mle, R mge, and R qme) used in [5]. All dwell times were assumed to follow the same law, but with different parameters, as well for the flight times.…”
Many studies propose strong user authentication based on biometric modalities. However, they often either, assume a trusted component, are modalitydependant, use only one biometric modality, are reversible, or does not enable the service to adapt the security on-the-fly. A recent work [1] introduced the concept of Personal Identity Code Respecting Privacy (PICRP), a non-cryptographic and nonreversible signature computed from any arbitrary information. In this paper, we extend this concept with the use of Keystroke Dynamics, IP and GPS geolocation by optimizing the pre-processing and merging of collected information. We demonstrate the performance of the proposed approach through experimental results and we present an example of its usage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.