Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems
This addresses safety analysis for engineers in safety-critical systems like autonomous vehicles, though it is incremental as it builds on existing simulator and retraining methods.
The paper tackles the problem of identifying and mitigating hazard-triggering events in DNN-based safety-critical systems by proposing SEDE, a technique that generates readable descriptions of commonalities in failure-inducing images and improves DNN accuracy through retraining, achieving up to 18 percentage points improvement.
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all failure-inducing images to determine common characteristics among them. Such characteristics correspond to hazard-triggering events (e.g., low illumination) that are essential inputs for safety analysis. Though informative, such activity is expensive and error-prone. To support such safety analysis practices, we propose SEDE, a technique that generates readable descriptions for commonalities in failure-inducing, real-world images and improves the DNN through effective retraining. SEDE leverages the availability of simulators, which are commonly used for cyber-physical systems. It relies on genetic algorithms to drive simulators towards the generation of images that are similar to failure-inducing, real-world images in the test set; it then employs rule learning algorithms to derive expressions that capture commonalities in terms of simulator parameter values. The derived expressions are then used to generate additional images to retrain and improve the DNN. With DNNs performing in-car sensing tasks, SEDE successfully characterized hazard-triggering events leading to a DNN accuracy drop. Also, SEDE enabled retraining leading to significant improvements in DNN accuracy, up to 18 percentage points.