Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO

We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions. This competition targets robustness and generalization in multi-agent systems: participants train teams of agents to complete a multi-task objective against opponents not seen during training. We summarize the competition design...

Policy-driven Data Sharing over Attribute-Based Encryption supporting Dual Membership

Attribute-Based Encryption (ABE) plays an important role in current secure data sharing through fine-grained customizable policies. However, the existing ABE schemes only support simple predicates, = and ≠, but cannot express a more general membership predicates, ∈ and ∉, in policies. The low expressivity of ABE will enlarge the ciphertext...