Mechanism for software tamper resistance

Abstract

In software protection we typically have to deal with the white-box attack model. In this model an attacker is assumed to have full access to the software and full control over its execution. The goal of white-box cryptography is to implement cryptographic algorithms in software such that it is hard for an attacker to extract the key by a white-box attack. Chow et al. present white-box implementations for AES and DES. Based on their ideas, white-box implementations can be derived for other block ciphers as well. In the white-box implementations the key of the underlying block cipher is expanded from several bytes to a collection of lookup tables with a total size in the order of hundreds of kilobytes. In this paper we present a technique that uses a white-box implementation to make software tamper resistant. The technique interprets the binary of software code as lookup tables, which are next incorporated into the collection of lookup tables of a white-box implementation. This makes the code tamper resistant as the dual interpretation implies that a change in the code results in an unintentional change in the white-box implementation. We also indicate in the paper that it is difficult for an attacker to make modifications to the white-box implementation such that its original operation is restored.