Verifying Properties of Tsetlin Machines
This work addresses the need for formal verification in interpretable machine learning, but it is incremental as it adapts existing verification notions to a specific model.
The authors tackled the problem of formally verifying properties of Tsetlin Machines, an interpretable machine learning method, by encoding them into propositional logic and using a SAT solver to check properties like adversarial robustness, equivalence, and similarity, with experiments on MNIST and IMDB datasets.
Tsetlin Machines (TsMs) are a promising and interpretable machine learning method which can be applied for various classification tasks. We present an exact encoding of TsMs into propositional logic and formally verify properties of TsMs using a SAT solver. In particular, we introduce in this work a notion of similarity of machine learning models and apply our notion to check for similarity of TsMs. We also consider notions of robustness and equivalence from the literature and adapt them for TsMs. Then, we show the correctness of our encoding and provide results for the properties: adversarial robustness, equivalence, and similarity of TsMs. In our experiments, we employ the MNIST and IMDB datasets for (respectively) image and sentiment classification. We discuss the results for verifying robustness obtained with TsMs with those in the literature obtained with Binarized Neural Networks on MNIST.