Using DeepProbLog to perform Complex Event Processing on an Audio Stream

In this paper, we present an approach to Complex Event Processing (CEP) that is based on DeepProbLog. This approach has the following objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining the flexibility and modularity on the definitions of complex event rules, (iii) allowing the system to be trained in an end-to-end manner and (iv) being robust against adversarial conditions. Our approach makes use of DeepProbLog to use a hybrid neuro-symbolic architecture that combines a neural network to process the symbolic data with a probabilistic logic layer to allow the user to define the rules for the complex events. We demonstrate that our approach is capable of detecting complex events from an audio stream. We also demonstrate that our approach is fairly robust against adversarial conditions by training it with datasets under different levels of poisoning attacks.