Adversarial robustness guarantees for classification with Gaussian Processes

Adversarial robustness guarantees for classification with Gaussian Processes

We investigate adversarial robustness of Gaussian Process classification (GPC) models. Specifically, given a compact subset of the input space T⊆ℝd enclosing a test point x∗ and a GPC trained on a dataset , we aim to compute the minimum and the maximum classification probability for the GPC over al...

Podrobná bibliografie
Hlavní autoři:	Blaas, A, Patane, A, Laurenti, L, Cardelli, L, Kwiatkowska, M, Roberts, S
Médium:	Conference item
Jazyk:	English
Vydáno:	Proceedings of Machine Learning Research 2020

Podobné jednotky

Adversarial robustness guarantees for Gaussian processes
Autor: Patane, A, a další
Vydáno: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
Autor: Cardelli, L, a další
Vydáno: (2019)

Safety guarantees for iterative predictions with Gaussian Processes
Autor: Polymenakos, K, a další
Vydáno: (2021)

Statistical guarantees for the robustness of Bayesian neural networks
Autor: Cardelli, L, a další
Vydáno: (2019)

On the adversarial robustness of Gaussian processes
Autor: Patanè, A
Vydáno: (2020)

Adversarial robustness certification for Bayesian neural networks
Autor: Wicker, M, a další
Vydáno: (2024)

Bayesian inference with certifiable adversarial robustness
Autor: Wicker, M, a další
Vydáno: (2021)

Individual fairness guarantees for neural networks
Autor: Benussi, E, a další
Vydáno: (2022)

Adversarially robust optimization with Gaussian processes
Autor: Bogunovic, I, a další
Vydáno: (2021)

Adversarially robust optimization with Gaussian processes
Autor: Bogunovic, Ilija, a další
Vydáno: (2022)

Gaussian processes with physiologically-inspired priors for physical arousal recognition
Autor: Ghiasi, S, a další
Vydáno: (2020)

Physiologically-informed Gaussian processes for interpretable modelling of psycho-physiological states
Autor: Ghiasi, S, a další
Vydáno: (2022)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
Autor: Michelmore, R, a další
Vydáno: (2020)

On the adversarial robustness of Bayesian machine learning models
Autor: Blaas, AC
Vydáno: (2021)

Adversarial Robustness Guarantees for Random Deep Neural Networks
Autor: De Palma, Giacomo, a další
Vydáno: (2022)

Robust optimization for adversarial learning with finite sample complexity guarantees
Autor: Bertolace, A, a další
Vydáno: (2024)

Robustness guarantees for deep neural networks on videos
Autor: Kwiatkowska, M, a další
Vydáno: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
Autor: Kwiatkowska, M
Vydáno: (2019)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
Autor: Kwiatkowska, M
Vydáno: (2020)

Provable guarantees on the robustness of decision rules to causal interventions
Autor: Wang, B, a další
Vydáno: (2021)

Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
Autor: Benjamin Appiah, a další
Vydáno: (2020-01-01)

On guaranteed optimal robust explanations for NLP models
Autor: La Malfa, E, a další
Vydáno: (2021)

Robustness of 3D deep learning in an adversarial setting
Autor: Wicker, M, a další
Vydáno: (2020)

Formal and efficient synthesis for continuous-time linear stochastic hybrid processes
Autor: Laurenti, L, a další
Vydáno: (2020)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
Autor: Kwiatkowska, M
Vydáno: (2022)

A language for modeling and optimizing experimental biological protocols
Autor: Cardelli, L, a další
Vydáno: (2021)

A Stochastic Hybrid Approximation for Chemical Kinetics Based on the Linear Noise Approximation
Autor: Cardelli, L, a další
Vydáno: (2016)

Programming discrete distributions with chemical reaction networks
Autor: Cardelli, L, a další
Vydáno: (2017)

Programming discrete distributions with chemical reaction networks
Autor: Cardelli, L, a další
Vydáno: (2016)

Stochastic analysis of chemical reaction networks using linear noise approximation
Autor: Cardelli, L, a další
Vydáno: (2016)

Scalable Gaussian process inference with finite-data mean and variance guarantees
Autor: Huggins, Jonathan H., a další
Vydáno: (2020)

Assessing robustness of text classification through maximal safe radius computation
Autor: La Malfa, E, a další
Vydáno: (2020)

Adversarial attacks on graph classification via Bayesian optimisation
Autor: Wan, X, a další
Vydáno: (2021)

Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
Autor: Desheng Wang, a další
Vydáno: (2023-03-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
Autor: Wijk, H, a další
Vydáno: (2022)

Probabilistic safety for bayesian neural networks
Autor: Wicker, M, a další
Vydáno: (2020)

Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
Autor: Arslan Ali, a další
Vydáno: (2023-03-01)

Central limit model checking
Autor: Bortolussi, L, a další
Vydáno: (2019)

Approximation of probabilistic reachability for chemical reaction networks using the linear noise approximation
Autor: Kwiatkowska, M, a další
Vydáno: (2016)

Central limit model checking
Autor: Bortolussi, L, a další
Vydáno: (2018)