collaborators

7 papers

cs.CV2026

Hybrid Robustness Verification for Spatio-Temporal Neural Networks

Sherwin Varghese, Matthew Wicker, Alessio Lomuscio

With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely o…

cs.LG2026

Certified Robustness to Data Poisoning in Gradient-Based Training

Philip Sosnin, Mark N. Müller, Maximilian Baader +2

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. P…

cs.LG2026

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers

Albus Yizhuo Li, Matthew Wicker

Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian me…

cs.LG2026

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning

Maksim Anisimov, Francesco Belardinelli, Matthew Wicker

Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments exhibit non-stationary dynamic…

cs.LG2026

Provably Safe Model Updates

Leo Elmecker-Plakolm, Pierre Fasterling, Philip Sosnin +2

Safety-critical environments are inherently dynamic. Distribution shifts, emerging vulnerabilities, and evolving requirements demand continuous updates to machine learning models.…

cs.LG2025

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

Philip Sosnin, Matthew Wicker, Josh Collyer +1

The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques fo…