A Subjective Logic-based method for runtime confidence updates in safety arguments
Researchers have developed a new method using Subjective Logic to dynamically update confidence in AI safety arguments during runtime. This approach integrates evidence from both the design phase and real-time performance indicators to continuously assess and adjust safety claims. The system is designed to be responsive, penalizing violations promptly while increasing confidence when safety is maintained, as demonstrated with a simulated construction zone assist function. AI
IMPACT Introduces a novel approach to continuously verify AI safety claims during operation, potentially improving real-world AI system reliability.