These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Hamming distance
In information theory, the Hamming distance between two strings of equal length is the number of positions at which the corresponding symbols are different. In other words, it measures the minimum number of substitutions required to change one string into the other, or the minimum number of errors that could have transformed one string into the other. In a more general context, the Hamming distance is one of several string metrics for measuring the edit distance between two sequences.
Hamming distance can support the Robustness objective by serving as a tool to measure how small changes in input data (e.g., bit flips or categorical changes) affect model outputs. This can help evaluate the resilience of AI systems to minor perturbations or adversarial attacks, thus contributing to the assessment and improvement of system robustness. However, this connection is indirect and context-dependent, as Hamming distance alone does not guarantee robustness but can be used as part of robustness testing.
About the metric
You can click on the links to see the associated metrics
Objective(s):
Purpose(s):
Lifecycle stage(s):
Target users:
