Kristian Schwethelm
YOU?
Author Swipe
View article: Laplace Sample Information: Data Informativeness Through a Bayesian Lens
Laplace Sample Information: Data Informativeness Through a Bayesian Lens Open
Accurately estimating the informativeness of individual samples in a dataset is an important objective in deep learning, as it can guide sample selection, which can improve model efficiency and accuracy by removing redundant or potentially…
View article: Differentially Private Active Learning: Balancing Effective Data Selection and Privacy
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy Open
Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods…
View article: Visual Privacy Auditing with Diffusion Models
Visual Privacy Auditing with Diffusion Models Open
Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees…
View article: From Mean to Extreme: Formal Differential Privacy Bounds on the Success of Real-World Data Reconstruction Attacks
From Mean to Extreme: Formal Differential Privacy Bounds on the Success of Real-World Data Reconstruction Attacks Open
The gold standard for privacy in machine learning, Differential Privacy (DP), is often interpreted through its guarantees against membership inference. However, translating DP budgets into quantitative protection against the more damaging …
View article: Fully Hyperbolic Convolutional Neural Networks for Computer Vision
Fully Hyperbolic Convolutional Neural Networks for Computer Vision Open
Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces. Howe…