Semi-invasive fault injection attacks, such as optical fault injection, are powerful techniques well-known by attackers and secure embedded system designers. When performing such attacks, the selection of the fault injection parameters is of utmost importance and usually based on the experience of the attacker. Surprisingly, there exists no formal and general approach on how to find such fault injection parameters.
In this work, we present a novel methodology to perform a fast characterization of the fault injection impact on a target, depending on the possible attack parameters.
We experimentally show our methodology to be a successful one when considering targets running DES and AES encryption.
Finally, we show how deep learning can help in estimating the full characterization on the basis of a limited number of measurements.