Related papers: Adaptive Concurrent Non-Malleability with Bare Pub…
Enforcing security requirements in networked information systems relies on security controls to mitigate the risks from increasingly dangerous threats. Configuring security controls is challenging; even nowadays, administrators must perform…
Networks are useful representations of many systems with interacting entities, such as social, biological and physical systems. Characterizing the meso-scale organization, i.e. the community structure, is an important problem in network…
In machine learning, no data point stands alone. We believe that context is an underappreciated concept in many machine learning methods. We propose Attention-Based Clustering (ABC), a neural architecture based on the attention mechanism,…
Concurrent pattern calculus (CPC) drives interaction between processes by comparing data structures, just as sequential pattern calculus drives computation. By generalising from pattern matching to pattern unification, interaction becomes…
We propose a new coherent state quantum key distribution protocol that eliminates the need to randomly switch between measurement bases. This protocol provides significantly higher secret key rates with increased bandwidths than previous…
In this paper we address the problem of large space consumption for protocols in the Bounded Retrieval Model (BRM), which require users to store large secret keys subject to adversarial leakage. We propose a method to derive keys for such…
Conformal prediction is a widely used method to quantify the uncertainty of a classifier under the assumption of exchangeability (e.g., IID data). We generalize conformal prediction to the Hidden Markov Model (HMM) framework where the…
We study sequential decision-making in batched nonparametric contextual bandits, where actions are selected over a finite horizon divided into a small number of batches. Motivated by constraints in domains such as medicine and marketing --…
The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach…
Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores…
Non-malleable codes protect against an adversary who can tamper with the coded message by using a tampering function in a specified function family, guaranteeing that the tampering result will only depend on the chosen function and not the…
Non-orthogonal multiple access (NOMA) and beamforming are well-established techniques for enabling massive connectivity in future wireless networks. However, many optimal beamforming solutions rely on highly complex iterative algorithms and…
Blockchains and other public ledger structures promise a new way to create globally consistent event logs and other records. We make use of this consistency property to detect and prevent man-in-the-middle attacks in a key exchange such as…
We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to…
In this study, we propose a novel data-driven reduced-order model for complex dynamics, including nonlinear, multi-attractor, multi-frequency, and multiscale behaviours. The starting point is a fully automatable cluster-based network model…
We consider a decentralized setup in which the participants collaboratively train and serve a large neural network, and where each participant only processes a subset of the model. In this setup, we explore the possibility of…
Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…
Developing concurrent software is challenging, especially if it has to run on modern architectures with Weak Memory Models (WMMs) such as ARMv8, Power, or RISC-V. For the sake of performance, WMMs allow hardware and compilers to…
Due to the widespread use of complex machine learning models in real-world applications, it is becoming critical to explain model predictions. However, these models are typically black-box deep neural networks, explained post-hoc via…
Bayesian Neural Networks (BNNs) can overcome the problem of overconfidence that plagues traditional frequentist deep neural networks, and are hence considered to be a key enabler for reliable AI systems. However, conventional hardware…