In this work, we provide a theoretical foundation for crafting transferable adversarial examples to entire hypothesis classes.

V alue factorisation is a useful technique for multi-agent reinforcement learning (MARL) in global reward game, however, its underlying mechanism is not yet fully understood. This paper studies a theoretical framework for value factorisation with interpretability via Shapley value theory.

Germany's Munich airport has reopened after several drone sightings forced it to close and cancel more than a dozen flights on Thursday night. At least 17 flights were grounded in Munich, affecting nearly 3,000 passengers, while the airport said it diverted a further 15 flights to nearby cities. On Friday, a spokesperson for German flag carrier Lufthansa said flight operations have since resumed according to schedule. There was no immediate confirmation of where the drones had come from. Several airports across Europe have closed down in recent weeks because of unidentified drones.

Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a number of effective attack and defense algorithms have been designed, but no certificate of robustness has been developed for GCN-based graph classification under topological perturbations with both local and global budgets. In this paper, we propose the first certificate for this problem. Our method is based on Lagrange dualization and convex envelope, which result in tight approximation bounds that are efficiently computable by dynamic programming. When used in conjunction with robust training, it allows an increased number of graphs to be certified as robust.

Two paradigms have been widely studied to deal with such uncertainty.