DeepAI AI Chat
Log In Sign Up

Specifying and Testing k-Safety Properties for Machine-Learning Models

by   Maria Christakis, et al.

Machine-learning models are becoming increasingly prevalent in our lives, for instance assisting in image-classification or decision-making tasks. Consequently, the reliability of these models is of critical importance and has resulted in the development of numerous approaches for validating and verifying their robustness and fairness. However, beyond such specific properties, it is challenging to specify, let alone check, general functional-correctness expectations from models. In this paper, we take inspiration from specifications used in formal methods, expressing functional-correctness properties by reasoning about k different executions, so-called k-safety properties. Considering a credit-screening model of a bank, the expected property that "if a person is denied a loan and their income decreases, they should still be denied the loan" is a 2-safety property. Here, we show the wide applicability of k-safety properties for machine-learning models and present the first specification language for expressing them. We also operationalize the language in a framework for automatically validating such properties using metamorphic testing. Our experiments show that our framework is effective in identifying property violations, and that detected bugs could be used to train better models.


page 1

page 2

page 3

page 4


Software Testing for Machine Learning

Machine learning has become prevalent across a wide variety of applicati...

MLCheck- Property-Driven Testing of Machine Learning Models

In recent years, we observe an increasing amount of software with machin...

CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators

The topic of provable deep neural network robustness has raised consider...

Automated Directed Fairness Testing

Fairness is a critical trait in decision making. As machine-learning mod...

Scaling up Memory-Efficient Formal Verification Tools for Tree Ensembles

To guarantee that machine learning models yield outputs that are not onl...

Verifying Fairness Properties via Concentration

As machine learning systems are increasingly used to make real world leg...

If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components

Machine Vision Components (MVC) are becoming safety-critical. Assuring t...