On the hardness of robust classification

On the hardness of robust classification

Taispeáin leaganacha eile (1)

It is becoming increasingly important to understand the vulnerability of machine learning models to adversarial attacks. In this paper we study the feasibility of adversarially robust learning from the perspective of computational learning theory, considering both sample and computational complexity...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Gourdeau, P, Kanade, V, Kwiatkowska, M, Worrell, J
Formáid:	Journal article
Teanga:	English
Foilsithe / Cruthaithe:	Journal of Machine Learning Research 2021

Míreanna comhchosúla

On the hardness of robust classification
de réir: Gourdeau, P, et al.
Foilsithe / Cruthaithe: (2019)

When are local queries useful for robust learning?
de réir: Gourdeau, P, et al.
Foilsithe / Cruthaithe: (2023)

Sample complexity bounds for robustly learning decision lists against evasion attacks
de réir: Gourdeau, P, et al.
Foilsithe / Cruthaithe: (2022)

Sample complexity of robust learning against evasion attacks
de réir: Gourdeau, P
Foilsithe / Cruthaithe: (2023)

Adversarial robustness guarantees for classification with Gaussian Processes
de réir: Blaas, A, et al.
Foilsithe / Cruthaithe: (2020)

Assessing robustness of text classification through maximal safe radius computation
de réir: La Malfa, E, et al.
Foilsithe / Cruthaithe: (2020)

MODERN CLASSIFICATION OF HARDNESS DETERMINATION METHODS
de réir: V. Moshchenok
Foilsithe / Cruthaithe: (2010-01-01)

Why Is Multiclass Classification Hard?
de réir: Pablo Del Moral, et al.
Foilsithe / Cruthaithe: (2022-01-01)

Safety and robustness for deep learning with provable guarantees (keynote)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2019)

Classification of hard materials for contract documentation /
de réir: Mohd. For Mohd. Amin 279725, et al.
Foilsithe / Cruthaithe: (2007)

Classification of hard materials for contract documentation /
de réir: 372062 Chua, Jerry Kuo Sheng
Foilsithe / Cruthaithe: (2004)

Robustness guarantees for deep neural networks on videos
de réir: Kwiatkowska, M, et al.
Foilsithe / Cruthaithe: (2020)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2020)

Robust decision pipelines: opportunities and challenges for AI in business process modelling
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2023)

Robustness of 3D deep learning in an adversarial setting
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2020)

Entrer en relation. Distribuer des repas aux personnes exilées à Ouistreham
de réir: Camille Gourdeau
Foilsithe / Cruthaithe: (2019-12-01)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
de réir: Kwiatkowska, M
Foilsithe / Cruthaithe: (2022)

Emotion Classification in Spanish: Exploring the Hard Classes
de réir: Aiala Rosá, et al.
Foilsithe / Cruthaithe: (2021-10-01)

Generating Hard Examples for Pixel-Wise Classification
de réir: Hyungtae Lee, et al.
Foilsithe / Cruthaithe: (2021-01-01)

A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions
de réir: Kabeh Mohsenzadegan, et al.
Foilsithe / Cruthaithe: (2021-10-01)

The king is naked: On the notion of robustness for natural language processing
de réir: La Malfa, E, et al.
Foilsithe / Cruthaithe: (2022)

Outlier-Robust Spatial Perception: Hardness, General-Purpose Algorithms, and Guarantees
de réir: Tzoumas, Vasileios, et al.
Foilsithe / Cruthaithe: (2021)

S/HIC: Robust Identification of Soft and Hard Sweeps Using Machine Learning.
de réir: Daniel R Schrider, et al.
Foilsithe / Cruthaithe: (2016-03-01)

Provable guarantees on the robustness of decision rules to causal interventions
de réir: Wang, B, et al.
Foilsithe / Cruthaithe: (2021)

Hard-Positive Prototypical Networks for Few-Shot Classification
de réir: Mahsa Fazaeli-Javan, et al.
Foilsithe / Cruthaithe: (2025-01-01)

PCA-based hard disk media defect classification
de réir: Zhang, Jian Liang
Foilsithe / Cruthaithe: (2009)

Classification of hard materials for contract documentation [compact disc] /
de réir: 372062 Chua, Jerry Kuo Sheng
Foilsithe / Cruthaithe: (2004)

Adversarial robustness certification for Bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2024)

Robustness guarantees for Bayesian inference with Gaussian processes
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2019)

Robust classification of neonatal apnoea-related desaturations.
de réir: Monasterio, V, et al.
Foilsithe / Cruthaithe: (2012)

Efficient synthesis of robust models for stochastic systems
de réir: Calinescu, R, et al.
Foilsithe / Cruthaithe: (2018)

Structure-aware robustness certificates for graph classification
de réir: Osselin, P, et al.
Foilsithe / Cruthaithe: (2023)

Robust Classification via Support Vector Machines
de réir: Alexandru V. Asimit, et al.
Foilsithe / Cruthaithe: (2022-08-01)

Deep Metric Learning with Online Hard Mining for Hyperspectral Classification
de réir: Yanni Dong, et al.
Foilsithe / Cruthaithe: (2021-04-01)

KNN-Based Algorithm of Hard Case Detection in Datasets for Classification
de réir: Anton Okhrimenko, et al.
Foilsithe / Cruthaithe: (2023-03-01)

Characterizing Vocal Repertoires--Hard vs. Soft Classification Approaches.
de réir: Philip Wadewitz, et al.
Foilsithe / Cruthaithe: (2015-01-01)

Automating airborne pollen classification: Identifying and interpreting hard samples for classifiers
de réir: Manuel Milling, et al.
Foilsithe / Cruthaithe: (2025-01-01)

Adversarial robustness guarantees for Gaussian processes
de réir: Patane, A, et al.
Foilsithe / Cruthaithe: (2022)

Bayesian inference with certifiable adversarial robustness
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2021)

Robust Model Selection for Classification of Microarrays
de réir: Ikumi Suzuki, et al.
Foilsithe / Cruthaithe: (2009-01-01)