Automatic Characterization of Exploitable Faults: A Machine Learning Approach

Characterization of the fault space of a cipher to filter out a set of faults potentially exploitable for fault attacks (FA), is a problem with immense practical value. A quantitative knowledge of the exploitable fault space is desirable in several applications, like security evaluation, cipher construction and implementation, design, and testing of countermeasures etc. In this work, we investigate this problem in the context of block ciphers. The formidable size of the fault space of a block cipher mandates the use of an automation to solve this problem, which should be able to characterize each individual fault instance quickly. On the other hand, the automation is expected to be applicable to most of the block cipher constructions. Existing techniques for automated fault attacks do not satisfy both of these goals simultaneously and hence are not directly applicable in the context of exploitable fault characterization. In this paper, we present a supervised machine learning (ML) assisted automated framework, which successfully addresses both of the criteria mentioned. The key idea is to extrapolate the knowledge of some existing FAs on a cipher to rapidly figure out new attack instances on the same. Experimental validation of the proposed framework on two state-of-the-art block ciphers – PRESENT and LED, establishes that our approach is able to provide fairly good accuracy in identifying exploitable fault instances at a reasonable cost. Finally, the effect of different S-Boxes on the fault space of a cipher is evaluated utilizing the framework.