No article text was recorded for this version.
high-dimensional geometric vulnerability
Version 1 of 134 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure
- Blog: Generalized No Free Lunch Theorem for Adversarial Robustness
- Blog: Fundamental limits on the robustness of image classifiers
- Blog: Is the volume of a credal set a good measure for epistemic uncertainty?
- Blog: Adversarial Spheres
- Blog: Adversarial Examples Are a Natural Consequence of Test Error in Noise
- Blog: Understanding the Limitations of Conditional Generative Models
- Blog: Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution
- Blog: On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems
- Blog: Analysis of Privacy Leakage in Federated Large Language Models
- Blog: Lower Bounds for Adversarially Robust PAC Learning
- Blog: Are adversarial examples inevitable?
- Blog: Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces
- Blog: Geometry-Aware Guided Loss for Deep Crack Recognition
- Blog: Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
- Blog: Certified Robustness against Sparse Adversarial Perturbations via Data Localization
- Blog: Experimental quantum adversarial learning with programmable superconducting qubits
- Blog: Provable Privacy Attacks on Trained Shallow Neural Networks
- Blog: Characterization of Overfitting in Robust Multiclass Classification
- Blog: Understanding Practical Membership Privacy of Deep Learning
- Blog: Computational Concentration of Measure: Optimal Bounds, Reductions, and More
- Blog: Learning and certification under instance-targeted poisoning
- Blog: Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling
- Blog: A New Defense Against Adversarial Images: Turning a Weakness into a Strength
- Blog: Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions
- Blog: Removal Attack and Defense on AI-generated Content Latent-based Watermarking
- Blog: The Price of Robustness: Stable Classifiers Need Overparameterization
- Blog: Improved Estimation of Concentration Under ℓp-Norm Distance Metrics Using Half Spaces
- Blog: Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
- Blog: How adversarial attacks can disrupt seemingly stable accurate classifiers
- Blog: GANTouch: An Attack-Resilient Framework for Touch-Based Continuous Authentication System
- Blog: Robust in practice: Adversarial attacks on quantum machine learning
- Blog: A single gradient step finds adversarial examples on random two-layers neural networks
- Blog: Fundamental Tradeoffs in Distributionally Adversarial Training
History & citation
Current · Permanent link
- This direction split from The Geometric Inevitability of Adversarial Examples (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_high_dimensional_geometric_vulnerability_0d701065,
title = {high-dimensional geometric vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-dimensional-geometric-vulnerability/rdr_0d701065534641bcafb711287847275a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_high_dimensional_geometric_vulnerability_0d701065_v1,
title = {high-dimensional geometric vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-dimensional-geometric-vulnerability/rdr_0d701065534641bcafb711287847275a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}