Abstract

When initializing cryptographic systems or running cryptographic protocols, the randomness of critical parameters, like keys or key components, is one of the most crucial aspects. But, randomly chosen parameters come with the intrinsic chance of duplicates, which finally may cause cryptographic systems including RSA, ElGamal and Zero-Knowledge proofs to become insecure. When concerning digital identifiers, we need uniqueness in order to correctly identify a specific action or object. Unfortunately we also need randomness here. Without randomness, actions become linkable to each other or to their initiator’s digital identity. So ideally the employed (cryptographic) parameters should fulfill two potentially conflicting requirements simultaneously: randomness and uniqueness. This article proposes an efficient mechanism to provide both attributes at the same time without highly constraining the first one and never violating the second one. After defining five requirements on random number generators and discussing related work, we will describe the core concept of the generation mechanism. Subsequently we will prove the postulated properties (security, randomness, uniqueness, efficiency and privacy protection) and present some application scenarios including system-wide unique parameters, cryptographic keys and components, identifiers and digital pseudonyms.

Highlights

  • Concerning cryptographic parameters, cryptographic keys and digital identifiers, randomness is the foremost requirement

  • In this article we will propose a solution for the problem of randomness vs. uniqueness: a scheme to generate provably system-wide unique, but highly random and unlinkable numbers which can be used as digital identifiers and cryptographic parameters and keys

  • We discovered that the concept of collision-free number generators (CFNG) could be quite useful in the field of unique identifiers as well

Read more

Summary

Introduction

Concerning cryptographic parameters, cryptographic keys and digital identifiers, randomness is the foremost requirement. With respect to cryptographic applications, the lack of sufficient randomness causes security risks which may result in faster attacks or completely compromised systems. In the field of digital identifiers, the lack of randomness may cause privacy problems, when identifyers (and actions) become linkable to each other or to the identity of a specific instance or person. Beside the positive effects of randomness mentioned above, random generation processes unavoidably come with the intrinsic risk of duplicates. These duplicate cryptographic parameters, cryptographic keys and digital identifiers can put the security of safety- or security-critical systems at risk as well

The Risks of Pure Randomness
The Problem of Randomness vs Uniqueness
Our Contribution
Requirements on Random Number Generators
Security
Randomness
Efficiency
Uniqueness
Cryptographic Preliminaries
Related Work
Method
The Concept of Collision-Free Numbers
Fields of Application
Unique Cryptographic Parameters and Keys
Unique Identifiers and Pseudonyms
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call