Related papers: Geometry-Aware Backdoor Attacks: Leveraging Curvat…

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success in the…

Non-Euclidean geometry has recently emerged as a powerful tool, offering new insights and applications in optical microcavities supporting Whispering Gallery Modes (WGMs). In this study, we extend the concept of polygonal microcavities to…

Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the…

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean…

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Object detection, for the most part, has been formulated in the euclidean space, where euclidean or spherical geodesic distances measure the similarity of an image region to an object class prototype. In this work, we study whether a…

Learning in hyperbolic spaces has attracted increasing attention due to its superior ability to model hierarchical structures of data. Most existing hyperbolic learning methods use fixed distance measures for all data, assuming a uniform…

A recent paper [CGT] studies the evolution of star-shaped mean convex hypersurfaces of the Euclidean space by a class of nonhomogeneous expanding curvature flows. In the present paper we consider the same problem in the real, complex and…

Learning the representation of data with hierarchical structures in the hyperbolic space attracts increasing attention in recent years. Due to the constant negative curvature, the hyperbolic space resembles tree metrics and captures the…

Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. Current mitigation strategies primarily rely on activating…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

The arrangement of network nodes in hyperbolic spaces has become a widely studied problem, motivated by numerous results suggesting the existence of hidden metric spaces behind the structure of complex networks. Although several methods…

Mathematical objects are generally abstract and not very approachable. Illustrations and interactive visualizations help both students and professionals to comprehend mathematical material and to work with it. This approach lends itself…

Embedding into hyperbolic space is emerging as an effective representation technique for datasets that exhibit hierarchical structure. This development motivates the need for algorithms that are able to effectively extract knowledge and…

Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a novel hyperbolic recommendation model that uses geometrical…

Particle physics classification often assumes flat geometry, ignoring the curved statistical structure of collision data. We present a geometric framework for Vector Boson Fusion Higgs classification that combines physics-inspired…

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the…

Geometric representation learning has recently shown great promise in several machine learning settings, ranging from relational learning to language processing and generative models. In this work, we consider the problem of performing…

Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been developed. Existing hyperbolic networks encode geometric priors not…