BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

As machine learning (ML) becomes pervasive in high performance computing, ML has found its way into safety-critical domains (e.g., autonomous vehicles). Thus the reliability of ML has grown in importance. Specifically, failures of ML systems can have catastrophic consequences, and can occur due to soft errors, which are increasing in frequency due to system scaling. Therefore, we need to evaluate ML systems in the presence of soft errors. In this work, we propose Biel, an efficient fault injector (FI) for finding the safety-critical bits in ML applications. We find the widely-used ML computations are often monotonic. Thus we can approximate the error propagation behavior of a ML application as a monotonic function. BinFI uses a binary-search like FI technique to pinpoint the safety-critical bits (also measure the overall resilience). BinFI identifies 99.56% of safety-critical bits (with 99.63% precision) in the systems, which significantly outperforms random FI, with much lower costs.