Abstract
AbstractElectronic documents constitute specific units of information, and protecting them against unauthorized access is a challenging task. This is because a password protected document may be stolen from its host computer or intercepted while on transfer and exposed to unlimited offline attacks. The key issue is, therefore, making document passwords hard to crack. We propose to augment a common text password authentication interface to encrypted documents with a biometric facial identity verification providing highly personalized security mechanism based on pseudo-identities. In consequence the encrypted document can be unlocked with the legitimate user’s face, while for everyone else stays encrypted with a hard to crack text password. This paper makes two contributions: (1) The proposed scheme enables password autofill without referring to any external service, which significantly limits the possibilities of an attack by adversaries when opening, reading and editing the protected document, (2) By the adoption of biometric verification techniques enabling fine-tuning of false acceptance and false rejection rates, it provides for responsible adaptation to users.
Publisher
Springer Science and Business Media LLC
Subject
Computer Networks and Communications,Hardware and Architecture,Media Technology,Software
Reference61 articles.
1. Adini Y, Moses Y, Ullman S (1997) Face recognition: the problem of compensating for changes in illumination direction. IEEE Trans Pattern Anal Mach Intell 19(7):721–732. https://doi.org/10.1109/34.598229
2. Apple Inc. Manage passwords using keychains on Mac. https://support.apple.com/guide/mac-help/use-keychains-to-store-passwords-mchlf375f392/mac. Accessed: 2019-12-31
3. Arora S, Liang Y, Ma T (2015) Why are deep nets reversible: A simple theory, with implications for training. CoRR arXiv:1511.05653
4. Behrmann J, Grathwohl W, Chen RTQ, Duvenaud D, Jacobsen J-H (2019) Invertible residual networks. In: Chaudhuri K, Salakhutdinov R (eds) Proc. 36th Int. Conf. on Machine Learning, vol 97. PMLR, Long Beach, pp 573–582. http://proceedings.mlr.press/v97/behrmann19a.html
5. Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720. https://doi.org/10.1109/34.598228