The State of Fault Injection Vulnerability Detection

Abstract

Fault injection is a well known method to test the robustness and security vulnerabilities of software. Fault injections can be explored by simulations (cheap, but not validated) and hardware experiments (true, but very expensive). Recent simulation works have started to apply formal methods to the detection, analysis, and prevention of fault injection attacks to address verifiability. However, these approaches are ad-hoc and extremely limited in architecture, fault model, and breadth of application. Further, there is very limited connection between simulation results and hardware experiments. Recent work has started to consider broad spectrum simulation approaches that can cover many fault models and relatively large programs. Similarly the connection between these broad spectrum simulations and hardware experiments is being validated to bridge the gap between the two approaches. This presentation highlights the latest developments in applying formal methods to fault injection vulnerability detection, and validating software and hardware results with one another.

SimpliFI: Hardware Simulation of Embedded Software Fault Attacks

“…In the past decade, multiple studies have focused on characterizing the effects of embedded software fault attacks on various platforms. While the results vary by platform, authors agree that most results can be explained by replacing the original instruction with a different one [10][11][12][13]. Hence, these results confirm empirically what we would expect to determine with SimpliFI in a simulation.…”