No abstract

No abstract

The proliferation of Internet of Things (IoT) devices has led to many applications, including smart homes, smart cities and smart industrial control systems. Attacks like Distributed Denial of Service, event control hijacking, spoofing, event replay and zero day attacks are prevalent in smart environments. Conventional Network Intrusion Detection Systems (NIDSs) are tedious to deploy in the smart environment because of numerous communication architectures, manufacturer policies, technologies, standards and application-specific services. To overcome these challenges, we modeled the operational behavior of IoT network events using timed ACs and proposed a novel hybrid NIDS in this paper. A web server is integrated with IoT devices for remote access, and Constrained Application Protocol is employed in inter- and intra-smart device communication. Experiments are conducted in real time to validate our proposal and achieve 99.17% detection accuracy and 0.01% false positives.

No abstract

No abstract

No abstract

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identify that learning all pair-wise part-whole relationships between capsules of successive layers is inefficient. Further, we also realise that the choice of prediction networks and the routing mechanism are both key to equivariance. Based on these, we propose an alternative framework for capsule networks that learns to projectively encode the manifold of pose-variations, termed the space-of-variation (SOV), for every capsule-type of each layer. This is done using a trainable, equivariant function defined over a grid of group-transformations. Thus, the prediction-phase of routing involves projection into the SOV of a deeper capsule using the corresponding function. As a specific instantiation of this idea, and also in order to reap the benefits of increased parametersharing, we use type-homogeneous group-equivariant convolutions of shallower capsules in this phase. We also introduce an equivariant routing mechanism based on degree-centrality. We show that this particular instance of our general model is equivariant, and hence preserves the compositional representation of an input under transformations. We conduct several experiments on standard object-classification datasets that showcase the increased transformation-robustness, as well as general performance, of our model to several capsule baselines.

No abstract