Evolving genetic algorithms for fault injection attacks

Genetic algorithms are used today to solve numerous difficult problems. However, it is often needed to specialize and adapt them further in order to successfully tackle some specific problem. One such example is the fault injection attack where the goal is to find a specific set of parameters that can lead to a successful cryptographic attack in a minimum amount of time. In this paper we address the process of the specialization of genetic algorithm from its standard form to the final, highly-specialized one. In this process we needed to customize crossover operator, add a mapping between the values in cryptographic domain and genetic algorithm domain and finally to adapt genetic algorithm to work on-the-fly. For the last phase of development we plan to go to the memetic algorithm by adding a local search strategy. Furthermore, we give a comparison between our algorithm and random search which is the mostly employed method for this problem at the moment. Our experiments show that our algorithm significantly outperforms the random search.