Buchumschlag

A practical approach to evaluating the adversarial distance for machine learning classifiers

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Siedel, Georg, Gupta, Ekagra, Morozov, Andrey
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing
von: Siedel, Georg, et al.
Veröffentlicht: (2025)

Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions
von: Siedel, Georg, et al.
Veröffentlicht: (2023)

Stylized Synthetic Augmentation further improves Corruption Robustness
von: Siedel, Georg, et al.
Veröffentlicht: (2025)

Trainwreck: A damaging adversarial attack on image classifiers
von: Zahálka, Jan
Veröffentlicht: (2023)

A comparative study on machine learning approaches for rock mass classification using drilling data
von: Hansen, Tom F., et al.
Veröffentlicht: (2024)

Spectral regularization for adversarially-robust representation learning
von: Yang, Sheng, et al.
Veröffentlicht: (2024)

Class incremental learning with probability dampening and cascaded gated classifier
von: Pomponi, Jary, et al.
Veröffentlicht: (2024)

Review of multimodal machine learning approaches in healthcare
von: Krones, Felix, et al.
Veröffentlicht: (2024)

Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning
von: Ziai, Amir, et al.
Veröffentlicht: (2024)

Open-world machine learning: A review and new outlooks
von: Zhu, Fei, et al.
Veröffentlicht: (2024)

Are classical deep neural networks weakly adversarially robust?
von: Sun, Nuolin, et al.
Veröffentlicht: (2025)

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
von: Fort, Stanislav, et al.
Veröffentlicht: (2024)

Towards more transferable adversarial attack in black-box manner
von: Lei, Chun Tong, et al.
Veröffentlicht: (2025)

Water quality polluted by total suspended solids classified within an Artificial Neural Network approach
von: Soto, I. Luviano, et al.
Veröffentlicht: (2024)

A hierarchical loss and its problems when classifying non-hierarchically
von: Wu, Cinna, et al.
Veröffentlicht: (2017)

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
von: Stalder, Nicolas, et al.
Veröffentlicht: (2026)

Efficient generative adversarial networks using linear additive-attention Transformers
von: Morales-Juarez, Emilio, et al.
Veröffentlicht: (2024)

SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction
von: Yin, Huilin, et al.
Veröffentlicht: (2024)

Sparse patches adversarial attacks via extrapolating point-wise information
von: Nemcovsky, Yaniv, et al.
Veröffentlicht: (2024)

Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
von: Mumuni, Fuseinin, et al.
Veröffentlicht: (2024)

In-distribution adversarial attacks on object recognition models using gradient-free search
von: Madan, Spandan, et al.
Veröffentlicht: (2021)

Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes
von: Martinetz, Julius, et al.
Veröffentlicht: (2024)

The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks
von: Bastounis, Alexander, et al.
Veröffentlicht: (2021)

Fusion of complementary 2D and 3D mesostructural datasets using generative adversarial networks
von: Dahari, Amir, et al.
Veröffentlicht: (2021)

Robust width: A lightweight and certifiable adversarial defense
von: Peck, Jonathan, et al.
Veröffentlicht: (2024)

An uncertainty-aware Bayesian framework for machine learning classification models: A case study in land cover classification
von: Bilson, Samuel, et al.
Veröffentlicht: (2025)

Detection of trade in products derived from threatened species using machine learning and a smartphone
von: Kulkarni, Ritwik, et al.
Veröffentlicht: (2025)

P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors
von: David, Lucas, et al.
Veröffentlicht: (2023)

Machine learning approach to brain tumor detection and classification
von: Oh, Alice, et al.
Veröffentlicht: (2024)

Quantum machine learning for image classification
von: Senokosov, Arsenii, et al.
Veröffentlicht: (2023)

Revising deep learning methods in parking lot occupancy detection
von: Martynova, Anastasia, et al.
Veröffentlicht: (2023)

Improving automatic detection of driver fatigue and distraction using machine learning
von: Wu, Dongjiang
Veröffentlicht: (2024)

A comparative study of generative adversarial networks for image recognition algorithms based on deep learning and traditional methods
von: Zhong, Yihao, et al.
Veröffentlicht: (2024)

Machine learning and machine learned prediction in chest X-ray images
von: Garrett, Shereiff, et al.
Veröffentlicht: (2025)

Benford's law: what does it say on adversarial images?
von: Zago, João G., et al.
Veröffentlicht: (2021)

Wasserstein distributional adversarial training for deep neural networks
von: Bai, Xingjian, et al.
Veröffentlicht: (2025)

How to predict on-road air pollution based on street view images and machine learning: a quantitative analysis of the optimal strategy
von: Zhong, Hui, et al.
Veröffentlicht: (2024)

ADBM: Adversarial diffusion bridge model for reliable adversarial purification
von: Li, Xiao, et al.
Veröffentlicht: (2024)

Deep semi-supervised approach based on consistency regularization and similarity learning for weeds classification
von: Benchallal, Farouq, et al.
Veröffentlicht: (2025)

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness
von: Ballarin, Emanuele, et al.
Veröffentlicht: (2023)