EagerNet: Early Predictions of Neural Networks for Computationally Efficient Intrusion Detection

Fully Connected Neural Networks (FCNNs) have been the core of most state-of-the-art Machine Learning (ML) applications in recent years and also have been widely used for Intrusion Detection Systems (IDSs). Experimental results from the last years show that generally deeper neural networks with more layers perform better than shallow models. Nonetheless, with the growing number of layers, obtaining fast predictions with less resources has become a difficult task despite the use of special hardware such as GPUs. We propose a new architecture to detect network attacks with minimal resources. The architecture is able to deal with either binary or multiclass classification problems and trades prediction speed for the accuracy of the network. We evaluate our proposal with two different network intrusion detection datasets. Results suggest that it is possible to obtain comparable accuracies to simple FCNNs without evaluating all layers for the majority of samples, thus obtaining early predictions and saving energy and computational efforts.

SparseIDS: Learning Packet Sampling with Reinforcement Learning

Recurrent Neural Networks (RNNs) have been shown to be valuable for constructing Intrusion Detection Systems (IDSs) for network data. They allow determining if a flow is malicious or not already before it is over, making it possible to take action immediately. However, considering the large number of packets that have to be inspected, the question of computational efficiency arises. We show that by using a novel Reinforcement Learning (RL)-based approach called SparseIDS, we can reduce the number of consumed packets by more than three fourths while keeping classification accuracy high. Comparing to various other sampling techniques, SparseIDS consistently achieves higher classification accuracy by learning to sample only relevant packets. A major novelty of our RL-based approach is that it can not only skip up to a predefined maximum number of samples like other approaches proposed in the domain of Natural Language Processing but can even skip arbitrarily many packets in one step. This enables saving even more computational resources for long sequences. Inspecting SparseIDS's behavior of choosing packets shows that it adopts different sampling strategies for different attack types and network flows. Finally we build an automatic steering mechanism that can guide SparseIDS in deployment to achieve a desired level of sparsity.