Fast and Accurate Error Simulation for CNNs against Soft Errors
This work addresses the reliability of CNNs for safety-critical applications, offering a more efficient and accurate simulation method, though it is incremental as it builds on existing error simulation strategies.
The paper tackles the problem of assessing the robustness of Convolutional Neural Networks (CNNs) against soft errors in hardware by developing an error simulation framework that bridges fault injection and error simulation, achieving about 99% accuracy compared to SASSIFI and speedups of 44x to 63x compared to TensorFI.
The great quest for adopting AI-based computation for safety-/mission-critical applications motivates the interest towards methods for assessing the robustness of the application w.r.t. not only its training/tuning but also errors due to faults, in particular soft errors, affecting the underlying hardware. Two strategies exist: architecture-level fault injection and application-level functional error simulation. We present a framework for the reliability analysis of Convolutional Neural Networks (CNNs) via an error simulation engine that exploits a set of validated error models extracted from a detailed fault injection campaign. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults and bridge the gap between fault injection and error simulation, exploiting the advantages of both approaches. We compared our methodology against SASSIFI for the accuracy of functional error simulation w.r.t. fault injection, and against TensorFI in terms of speedup for the error simulation strategy. Experimental results show that our methodology achieves about 99\% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t. TensorFI, that only implements a limited set of error models.