Autoencoders are popular neural networks that are able to compress high dimensional data to extract relevant latent information. TabNet is a state-of-the-art neural network model designed for tabular data that utilizes an autoencoder architecture for training. Vertical Federated Learning (VFL) is an emerging distributed machine learning paradigm that allows multiple parties to train a model collaboratively on vertically partitioned data while maintaining data privacy. The existing design of training autoencoders in VFL is to train a separate autoencoder in each participant and aggregate the latent representation later. This design could potentially break important correlations between feature data of participating parties, as each autoencoder is trained on locally available features while disregarding the features of others. In addition, traditional autoencoders are not specifically designed for tabular data, which is ubiquitous in VFL settings. Moreover, the impact of client failures during training on the model robustness is under-researched in the VFL scene. In this paper, we propose TabVFL, a distributed framework designed to improve latent representation learning using the joint features of participants. The framework (i) preserves privacy by mitigating potential data leakage with the addition of a fully-connected layer, (ii) conserves feature correlations by learning one latent representation vector, and (iii) provides enhanced robustness against client failures during training phase. Extensive experiments on five classification datasets show that TabVFL can outperform the prior work design, with 26.12% of improvement on f1-score.

Information-Centric Networking (ICN) is a new approach for a more scalable and effective internet. ICN has many benefits, namely: ubiquitous caching, location-independent content routing and content-centric security. Despite the aforementioned benefits, the network paradigm is not ready to replace the current host-centric network as ICN is relatively new and has many security and privacy flaws. In this paper, an overview of how ICN works is given with its benefits and challenges compared to the host-centric paradigm. The most important state-of-the-art security and privacy attacks are analysed and investigated. Those consist of interest flooding, cache pollution, censorship and timing attack. The existent mitigation methods are also described for each attack. The paper also proposes an improved version of an existing defence mechanism for the timing attack. Lastly, the conclusion is drawn and future work is discussed.