A Predictive Approach for the Early Reliability Assessment in Embedded Systems Using Code and Trace Embeddings via Machine Learning

Radiation-induced transient faults pose a growing challenge for safety-critical embedded systems, yet traditional radiation testing and large-scale statistical fault injection (SFI) remain costly and impractical during early design stages. This paper presents a predictive approach for early reliability assessment that replaces handcrafted feature engineering with automatically learned vector representations of source code and execution traces. We derive multiple embeddings for traces and source code, and use them as inputs to a family of regression models, including ensemble methods and linear baselines, to build predictive models for reliability. Experimental evaluation shows that embedding-based models outperform prior approaches, reducing the mean absolute percentage error (MAPE) from 6.24% to 2.14% for correct executions (unACE), from 20.95% to 10.40% for Hangs, and from 49.09% to 37.69% for silent data corruptions (SDC) after excluding benchmarks with SDC below 1%. These results show that source code and trace embeddings can serve as effective estimators for expensive fault injection campaigns, enabling early-stage reliability assessment in radiation-exposed embedded systems without requiring any manual feature engineering. This capability provides a practical foundation for supporting design-space exploration during early development phases.