English
Related papers

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

200 papers

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers…

Machine Learning · Computer Science 2019-10-30 Ines Chami , Rex Ying , Christopher Ré , Jure Leskovec

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Jeongjin Shin

Interior-point methods (IPMs) are a cornerstone of Euclidean convex optimization, due to their strong theoretical guarantees and practical performance. Motivated by scaling problems, recent work by Hirai and the last two authors (FOCS'23)…

Optimization and Control · Mathematics 2026-04-09 Christopher Criscitiello , Harold Nieuwboer , Michael Walter

Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space. However, the necessity of hyperbolic space in KGE is still questionable, because the calculation…

Artificial Intelligence · Computer Science 2021-10-26 Kai Wang , Yu Liu , Dan Lin , Quan Z. Sheng

Non-adiabatic and non-closed evolutionary paths play a significant role in the fidelity of quantum gates. We propose a high-fidelity quantum control framework based on the quasi-topological number ($\nu_{\text{qua}}$), which extends the…

Quantum Physics · Physics 2026-03-10 Ximo Wang , Hongyan Fan , Zhengqi Bai , Yichi Zhang

Adversarial machine learning has exposed several security hazards of neural models and has become an important research topic in recent times. Thus far, the concept of an "adversarial perturbation" has exclusively been used with reference…

Machine Learning · Computer Science 2020-09-22 Siddhant Garg , Adarsh Kumar , Vibhor Goel , Yingyu Liang

Do contemporary diffusion models preserve the class geometry of hyperspherical data? Standard diffusion models rely on isotropic Gaussian noise in the forward process, inherently favoring Euclidean spaces. However, many real-world problems…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Muskan Dosi , Chiranjeev Chiranjeev , Kartik Thakral , Mayank Vatsa , Richa Singh

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

Machine Learning · Computer Science 2021-07-14 Jing Xu , Minhui , Xue , Stjepan Picek

Understanding body part geometry is crucial for precise medical diagnostics. Curves effectively describe anatomical structures and are widely used in medical imaging applications related to cardiovascular, respiratory, and skeletal…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Farukh Yaushev , Daria Nogina , Valentin Samokhin , Mariya Dugova , Ekaterina Petrash , Dmitry Sevryukov , Mikhail Belyaev , Maxim Pisov

New quadrotor UAV control algorithms are developed, based on nonlinear surfaces composed of tracking errors that evolve directly on the nonlinear configuration manifold, thus inherently including in the control design the nonlinear…

Systems and Control · Computer Science 2018-11-13 Michalis Ramp , Evangelos Papadopoulos

Let $(M, \partial M)$ be a compact 3-manifold with boundary which admits a complete, convex co-compact hyperbolic metric. For each hyperbolic metric $g$ on $M$ such that $\dr M$ is smooth and strictly convex, the induced metric on $\dr M$…

Geometric Topology · Mathematics 2007-05-23 Jean-Marc Schlenker

Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed hierarchical or tree-like data. In particular, the few past…

Machine Learning · Computer Science 2023-06-16 Eric Qu , Dongmian Zou

We demonstrate that higher-order electric susceptibilities in crystals can be enhanced and understood through nontrivial topological invariants and quantum geometry, using one-dimensional $\pi$-conjugated chains as representative model…

Mesoscale and Nanoscale Physics · Physics 2025-09-18 Wojciech J. Jankowski , Robert-Jan Slager , Michele Pizzochero

Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yi Yu , Yufei Wang , Wenhan Yang , Lanqing Guo , Shijian Lu , Ling-Yu Duan , Yap-Peng Tan , Alex C. Kot

This paper continues a geometric study of Harvey's Complex of Curves, whose ultimate goal is to apply the theory of hyperbolic spaces and groups to algorithmic questions for the Mapping Class Group and geometric properties of Kleinian…

Geometric Topology · Mathematics 2007-05-23 Howard A. Masur , Yair N. Minsky

Protein-ligand binding prediction is central to virtual screening and affinity ranking, two fundamental tasks in drug discovery. While recent retrieval-based methods embed ligands and protein pockets into Euclidean space for…

Machine Learning · Computer Science 2025-11-25 Jianhui Wang , Wenyu Zhu , Bowen Gao , Xin Hong , Ya-Qin Zhang , Wei-Ying Ma , Yanyan Lan

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Mozhgan Pourkeshavarz , Mohammad Sabokrou , Amir Rasouli

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

We relate three classes of nonpositively curved metric spaces: hierarchically hyperbolic spaces, coarsely injective spaces, and strongly shortcut spaces. We show that every hierarchically hyperbolic space admits a new metric that is…

Group Theory · Mathematics 2023-06-21 Thomas Haettel , Nima Hoda , Harry Petyt

A geometric transition is a continuous path of geometric structures that changes type, meaning that the model geometry, i.e. the homogeneous space on which the structures are modeled, abruptly changes. In order to rigorously study…

Geometric Topology · Mathematics 2014-12-15 Daryl Cooper , Jeffrey Danciger , Anna Wienhard
‹ Prev 1 8 9 10 Next ›