Catalogue of Tools & Metrics for Trustworthy AI

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.

Scope

SUBMIT A METRIC

If you have a tool that you think should be featured in the Catalogue of AI Tools & Metrics, we would love to hear from you!

SUBMIT
This page includes technical metrics and methodologies for measuring and evaluating AI trustworthiness and AI risks. These metrics are often represented through mathematical formulas that assess the technical requirements for achieving trustworthy AI in a particular context. They can help to ensure that a system is fair, accurate, explainable, transparent, robust, safe, or secure.

Accuracy is the proportion of correct predictions among the total number of cases processed. It can be computed with:

Accuracy = (TP + TN) / (TP + TN + FP + FN) , where:

TP: True positive

TN: True negative

FP: False positive

FN...

Objectives:


Mean Intersection over Union (IoU) is the area of overlap between the predicted segmentation and the ground truth divided by the area of union between the predicted segmentation and the ground truth.

For binary (two classes) or multi-class segmentatio...

Objectives:


Mahalonobis distance is the distance between a point and a distribution (as opposed to the distance between two points), making it the multivariate equivalent of the Euclidean distance.

It is often used in multivariate anomaly detection, classificatio...

Objectives:


The anonymity set for an individual u, denoted ASu is the set of users that the adversary cannot distinguish from u. It can be seen as the size of the crowd into which the target u can blend.


privASS ≡ |ASu |

...

If a model systematically makes errors disproportionately for patients in the protected group, it is likely to lead to unequal outcomes. Equal performance refers to the assurance that a model is equally accurate for patients in the protec...

Objectives:


This metric computes the area under the curve (AUC) for the Receiver Operating Characteristic Curve (ROC). The return values represent how well the model used is predicting the correct classes, based on the input data. A score of 0.5 means that the model is...

Objectives:


Bilingual Evaluation Understudy (BLEU) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Quality is considered to be the correspondence between a machine’s output and that of a human: ...

Objectives:


The most general time-based metric measures the time until the adversary’s success. It assumes that the adversary will succeed eventually, and is therefore an example of a pessimistic metric. This metric relies on a definition of success, and varies depend...


This metric counts the information items S disclosed by a system, e.g., the number of compromised users. However, this metric does not indicate the severity of a leak because it does not account for the
sensitivity of the leaked information.

<...


Precision is the fraction of correctly labeled positive examples out of all of the examples that were labeled as positive. It is computed via the equation: Precision = TP / (TP + FP) where TP is the True positives (i.e. the examples correctly labeled as pos...

Objectives:


ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics and a software package used for evaluating automatic summarization and machine translation software in natural language processing. The metrics compare an automatically produce...

Objectives:


Recall is the fraction of the positive examples that were correctly labeled by the model as positive. It can be computed with the equation: Recall = TP / (TP + FN) Where TP is the number of true positives and FN is the number of false negatives.

Objectives:


This paper proposes a new bias evaluation metric – Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of...

Objectives:


The CIDEr (Consensus-based Image Description Evaluation) metric is a way of evaluating the quality of generated textual descriptions of images. The CIDEr metric measures the similarity between a generated caption and the reference captions, and it is based ...

Objectives:


Word Error Rate (WER) is a common metric of the performance of an automatic speech recognition (ASR) system.

The general difficulty of measuring the performance of ASR systems lies in the fact that the recognized word sequence can have a different len...

Objectives:


SacreBLEU provides hassle-free computation of shareable, comparable, and reproducible BLEU scores. Inspired by Rico Sennrich’s multi-bleu-detok.perl, it produces the official Workshop on Machine Translation (WMT) scores but works with plain text. It also kn...

Objectives:


Given a model and an input text sequence, perplexity measures how likely the model is to generate the input text sequence. This can be used in two main ways: 

- to evaluate how well the model has learned the distribution of the text it was traine...

Objectives:


A given predicted string’s exact match score is 1 if it is the exact same as its reference string, and is 0 otherwise.

  • Example 1: The exact match score of prediction “Happy Birthday!” is 0, given its reference is “Happy New Year!...

Objectives:


The Adjusted Rand Index (ARI) is a measure of the similarity between two data clusterings. It is a correction of the Rand Index, which is a basic measure of similarity between two clusterings, but it has the disadvantage of being sensitive to chance. The Ad...

Objectives:


In statistical analysis of binary classification, the F-score or F-measure is a measure of a test's accuracy. It is calculated from the precision and recall of the test, where the precision is the number of true positive results divided by the number of all...

Objectives:


catalogue Logos

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.