Bayesian inference with certifiable adversarial robustness

Bayesian inference with certifiable adversarial robustness

We consider adversarial training of deep neural networks through the lens of Bayesian learning and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. We rely on techniques from constraint relaxation of non-convex optimisation probl...

Descrizione completa

Dettagli Bibliografici
Autori principali:	Wicker, M, Laurenti, L, Patane, A, Chen, Z, Zhang, Z, Kwiatkowska, M
Natura:	Conference item
Lingua:	English
Pubblicazione:	Journal of Machine Learning Research 2021

Documenti analoghi

Adversarial robustness certification for Bayesian neural networks
di: Wicker, M, et al.
Pubblicazione: (2024)

Robustness guarantees for Bayesian inference with Gaussian processes
di: Cardelli, L, et al.
Pubblicazione: (2019)

Statistical guarantees for the robustness of Bayesian neural networks
di: Cardelli, L, et al.
Pubblicazione: (2019)

Adversarial robustness guarantees for Gaussian processes
di: Patane, A, et al.
Pubblicazione: (2022)

Probabilistic safety for bayesian neural networks
di: Wicker, M, et al.
Pubblicazione: (2020)

Adversarial robustness of Bayesian neural networks
di: Wicker, M
Pubblicazione: (2021)

Adversarial robustness guarantees for classification with Gaussian Processes
di: Blaas, A, et al.
Pubblicazione: (2020)

Robustness of Bayesian neural networks to gradient-based attacks
di: Carbone, G, et al.
Pubblicazione: (2020)

Robustness of 3D deep learning in an adversarial setting
di: Wicker, M, et al.
Pubblicazione: (2020)

Certification of iterative predictions in Bayesian neural networks
di: Wicker, M, et al.
Pubblicazione: (2021)

Probabilistic reach-avoid for Bayesian neural networks
di: Wicker, M, et al.
Pubblicazione: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
di: Jiehang Zeng, et al.
Pubblicazione: (2023-06-01)

On the adversarial robustness of Gaussian processes
di: Patanè, A
Pubblicazione: (2020)

Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
di: Everett, Michael F, et al.
Pubblicazione: (2021)

Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
di: Everett, Michael, et al.
Pubblicazione: (2021)

Individual fairness guarantees for neural networks
di: Benussi, E, et al.
Pubblicazione: (2022)

Robust load forecasting towards adversarial attacks via Bayesian learning
di: Zhou, Y, et al.
Pubblicazione: (2022)

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

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
di: Laurenti, L, et al.
Pubblicazione: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
di: Laurenti, L, et al.
Pubblicazione: (2017)

Time Series Forecasting with Missing Data Using Generative Adversarial Networks and Bayesian Inference
di: Xiaoou Li
Pubblicazione: (2024-04-01)

Adversarially Robust Fault Zone Prediction in Smart Grids With Bayesian Neural Networks
di: Emad Efatinasab, et al.
Pubblicazione: (2024-01-01)

Trustworthiness and certified robustness for deep learning
di: Xia, Song
Pubblicazione: (2022)

Certifiable Outlier-Robust Geometric Perception
di: Yang, Heng
Pubblicazione: (2023)

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

Certifiers make neural networks vulnerable to availability attacks
di: Lorenz, T, et al.
Pubblicazione: (2023)

Robust simulation-based inference in cosmology with Bayesian neural networks
di: Pablo Lemos, et al.
Pubblicazione: (2023-01-01)

Adversarial Inference Control in Cyber-Physical Systems: A Bayesian Approach With Application to Smart Meters
di: Ramana R. Avula, et al.
Pubblicazione: (2024-01-01)

Inferring adversarial behaviour in cyber‐physical power systems using a Bayesian attack graph approach
di: Abhijeet Sahu, et al.
Pubblicazione: (2023-06-01)

AutoBayes: Automated Bayesian Graph Exploration for Nuisance- Robust Inference
di: Andac Demir, et al.
Pubblicazione: (2021-01-01)

Adversarial attacks and adversarial robustness in computational pathology
di: Narmin Ghaffari Laleh, et al.
Pubblicazione: (2022-09-01)

Towards Fast computation of certified robustness for ReLU networks
di: Weng, Tsui-Wei, et al.
Pubblicazione: (2021)

ME-Net: Towards effective adversarial robustness with matrix estimation
di: Yang, Y, et al.
Pubblicazione: (2021)

Bayesian inference in FMRI.
di: Woolrich, M
Pubblicazione: (2012)

Bayesian inference in FMRI
di: Woolrich, M
Pubblicazione: (2012)

On the adversarial robustness of aerial detection
di: Yuwei Chen, et al.
Pubblicazione: (2024-11-01)

Multivariate Financial Time-Series Prediction With Certified Robustness
di: Hui Li, et al.
Pubblicazione: (2020-01-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
di: Wijk, H, et al.
Pubblicazione: (2022)

Manifold-driven decomposition for adversarial robustness
di: Wenjia Zhang, et al.
Pubblicazione: (2024-01-01)

The R Package MitISEM: Efficient and Robust Simulation Procedures for Bayesian Inference
di: Nalan Baştürk, et al.
Pubblicazione: (2017-07-01)