Machine learning models are increasingly used in critical applications but are mostly ''black boxes'' due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex models near a test instance using simple, interpretable models. However, these approaches often suffer from instability and poor local fidelity. In this paper, we propose a novel approach called Adversarially Bracketed Local Explanation (ABLE) to address these limitations. Our approach first generates a set of neighborhood points near the test instance, xtest, by adding bounded Gaussian noise. For each neighborhood point D, we apply an adversarial attack to generate an adversarial point A with minimal perturbation that results in a different label than D. A second adversarial attack is then performed on A to generate a point A' that has the same label as D (and thus different than A). The points A and A' form an adversarial pair that brackets the local decision boundary for xtest. We then train a linear model on these adversarial pairs to approximate the local decision boundary. Experimental results on six UCI benchmark datasets across three deep neural network architectures demonstrate that our approach achieves higher stability and fidelity than the state-of-the-art.

In machine learning, hyperparameter optimization (HPO) is essential for effective model training and significantly impacts model performance. Hyperparameters are predefined model settings which fine-tune the model's behavior and are critical to modeling complex data patterns. Traditional HPO approaches such as Grid Search, Random Search, and Bayesian Optimization have been widely used in this field. However, as datasets grow and models increase in complexity, these approaches often require a significant amount of time and resources for HPO. This research introduces a novel approach using t-way testing---a combinatorial approach to software testing used for identifying faults with a test set that covers all t-way interactions---for HPO. T-way testing substantially narrows the search space and effectively covers parameter interactions. Our experimental results show that our approach reduces the number of necessary model evaluations and significantly cuts computational expenses while still outperforming traditional HPO approaches for the models studied in our experiments.

Machine learning (ML)-based models are often black box, making it challenging to understand and interpret their decision-making processes. Surrogate models are constructed to approximate the behavior of a target model and are an essential tool for analyzing black-box models. The construction of a surrogate model typically includes querying the target model with carefully selected data points and using the responses from the target model to infer information about its structure and parameters.