MWMatthew Wicker

Matthew Wicker

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Matthew Wicker has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hybrid Robustness Verification for Spatio-Temporal Neural Networks

    by Sherwin Varghese, Matthew Wicker, Alessio Lomuscio

  • Open Access

    Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy

    by Philip Sosnin, Matthew Wicker, Josh Collyer, Calvin Tsay

    The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques for adversarial robustness. In contrast, certifying models against training data perturbations remains a relatively under-explored area. These perturbations can arise in three critical contexts: adversarial data poisoning, where an adversary manipulates training samples to corrupt model performance; machine unlearning, which requires certifying model behavior under the removal of specific training data; and differential privacy, where guarantees must be given with respect to substituting individual data points. This work introduces Abstract Gradient Training (AGT), a unified framework for certifying robustness of a given model and training procedure to training data perturbations, including bounded perturbations, the removal of data points, and the addition of new samples. By bounding the reachable set of parameters, i.e., establishing provable parameter-space bounds, AGT provides a formal approach to analyzing the behavior of models trained via first-order optimization methods.

  • Open Access

    Adversarial Robustness Certification for Bayesian Neural Networks

    by Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska

    We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Specifically, we define two notions of robustness for BNNs in an adversarial setting: probabilistic robustness and decision robustness. The former deals with the probabilistic behaviour of the network, that is, it ensures robustness across different stochastic realisations of the network, while the latter provides guarantees for the overall (output) decision of the BNN. Although these robustness properties cannot be computed analytically, we present a unified computational framework for efficiently and formally bounding them. Our approach is based on weight interval sampling, integration and bound propagation techniques, and can be applied to BNNs with a large number of parameters independently of the (approximate) inference method employed to train the BNN. We evaluate the effectiveness of our method on tasks including airborne collision avoidance, medical imaging and autonomous driving, demonstrating that it can compute non-trivial guarantees on medium size images (i.e., over 16 thousand input parameters).