A Secure Mobile Authentication Alternative to Biometrics

Azimpourkivi, Mozhgan; Topkara, Umut; Cărbunar, Bogdan

doi:10.1145/3134600.3134619

Cited by 10 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [8], the authors introduce a novel authentication system, called ai.lock, for mobile devices which uses an imaging sensor for authentication. To extract invariant features for image-based authentication, LSH is used along with deep neural networks and Principal Component Analysis (PCA).…”

Section: Security/privacy Relatedmentioning

confidence: 99%

A Survey on Locality Sensitive Hashing Algorithms and their Applications

Jafari¹,

Maurya²,

Nagarkar³

et al. 2021

Preprint

View full text Add to dashboard Cite

Finding nearest neighbors in high-dimensional spaces is a fundamental operation in many diverse application domains. Locality Sensitive Hashing (LSH) is one of the most popular techniques for finding approximate nearest neighbor searches in high-dimensional spaces. The main benefits of LSH are its sub-linear query performance and theoretical guarantees on the query accuracy. In this survey paper, we provide a review of state-of-the-art LSH and Distributed LSH techniques. Most importantly, unlike any other prior survey, we present how Locality Sensitive Hashing is utilized in different application domains.CCS Concepts: • General and reference → Surveys and overviews.

show abstract

Section: Security/privacy Relatedmentioning

confidence: 99%

A Survey on Locality Sensitive Hashing Algorithms and their Applications

Jafari¹,

Maurya²,

Nagarkar³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another soft biometric is gait, i.e., how people walk. [7]. They use an InceptionV3 CNN [7] to derive features from pictures a mobile phone user takes.…”

Section: Classification On Spatial Datamentioning

confidence: 99%

“…[7]. They use an InceptionV3 CNN [7] to derive features from pictures a mobile phone user takes. The Inception architecture introduced inception modules, which consist of multiple convolutional filters of different sizes.…”

Section: Classification On Spatial Datamentioning

confidence: 99%

Deep Learning in Information Security

Thaler,

Menkovski,

Petkovic

2018

Preprint

View full text Add to dashboard Cite

Machine learning has a long tradition of helping to solve complex information security problems that are difficult to solve manually. Machine learning techniques learn models from data representations to solve a task. These data representations are hand-crafted by domain experts. Deep Learning is a sub-field of machine learning, which uses models that are composed of multiple layers. Consequently, representations that are used to solve a task are learned from the data instead of being manually designed. In this survey, we study the use of DL techniques within the domain of information security. We systematically reviewed 77 papers and presented them from a data-centric perspective. This data-centric perspective reflects one of the most crucial advantages of DL techniques -domain independence. If DL-methods succeed to solve problems on a data type in one domain, they most likely will also succeed on similar data from another domain. Other advantages of DL methods are unrivaled scalability and efficiency, both regarding the number of examples that can be analyzed as well as with respect of dimensionality of the input data. DL methods generally are capable of achieving high-performance and generalize well. However, information security is a domain with unique requirements and challenges. Based on an analysis of our reviewed papers, we point out shortcomings of DL-methods to those requirements and discuss further research opportunities.

show abstract

“…The use of biometrics is considered as the most secured among these authentication mechanisms [3]. However, according to [4], biometrics are hard to keep secret, stolen biometrics pose lifelong security risks to users as they cannot be reset and re-issued. Furthermore, transactions authenticated by biometrics across different systems are linkable and traceable back to the individual identity (in other words they don't preserve the user's privacy).…”

Section: Introductionmentioning

confidence: 99%

WYK: Mobile Device Authentication Using the User’s Address Book

Msgna

Katsikas

Gkioulos

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Authenticating a user the correct way is paramount to IT systems, where the risk is growing more and more in number and complexity. This is specially important in mobile phones, where a number of applications require continuous device authentication following the Point-of-Entry user authentication. Existing common approach in systems that require strict security rules and regulations is to use a One-Time-Password (OTP). Usually the OTP is generated using a special hardware device or another application that is synchronised with the back-end system. Another approach is to use SMS based activation/approval codes such as used by Telegram, Facebook, Twitter and other social media platforms. However, this approach has three major drawbacks; (1) it requires active user participation/interaction which could be annoying if repeated continuously, (2) SMS messages can be accessed by service provider's employees, and (3) it does not consider the authenticity of the device from which the services are being accessed. The later is particularly serious as access sessions can be hijacked by malicious entities. In this paper, we investigate the possibility of using the user's address book (contacts list) to continuously authenticate the device to ensure the services are only accessed the mobile phone that belongs to the legitimate user. We call this authentication the Who-You-Know (WYK) scheme. For our research, we developed three components, the WYK-Mobile-Service, WYK-API-Server and a Mobile-Demo-Application. The WYK-API-Server exposes a set of authentication server APIs and the WYK-Mobile-Service consumes these APIs to authenticate the device every time the mobile applications are launched and make a request to the API server. Finally, the Mobile-Demo-Application will extract user's data from the server if the device is successfully authenticated.

show abstract

A Secure Mobile Authentication Alternative to Biometrics

Cited by 10 publications

References 52 publications

A Survey on Locality Sensitive Hashing Algorithms and their Applications

A Survey on Locality Sensitive Hashing Algorithms and their Applications

Deep Learning in Information Security

WYK: Mobile Device Authentication Using the User’s Address Book

Contact Info

Product

Resources

About