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...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Wicker, M, Laurenti, L, Patane, A, Chen, Z, Zhang, Z, Kwiatkowska, M
Formáid:	Conference item
Teanga:	English
Foilsithe / Cruthaithe:	Journal of Machine Learning Research 2021

Míreanna comhchosúla

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)

Statistical guarantees for the robustness of Bayesian neural networks
de réir: Cardelli, L, et al.
Foilsithe / Cruthaithe: (2019)

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

Probabilistic safety for bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2020)

Adversarial robustness of Bayesian neural networks
de réir: Wicker, M
Foilsithe / Cruthaithe: (2021)

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

Robustness of Bayesian neural networks to gradient-based attacks
de réir: Carbone, G, et al.
Foilsithe / Cruthaithe: (2020)

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

Certification of iterative predictions in Bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2021)

Probabilistic reach-avoid for Bayesian neural networks
de réir: Wicker, M, et al.
Foilsithe / Cruthaithe: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
de réir: Jiehang Zeng, et al.
Foilsithe / Cruthaithe: (2023-06-01)

On the adversarial robustness of Gaussian processes
de réir: Patanè, A
Foilsithe / Cruthaithe: (2020)

Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
de réir: Everett, Michael F, et al.
Foilsithe / Cruthaithe: (2021)

Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
de réir: Everett, Michael, et al.
Foilsithe / Cruthaithe: (2021)

Individual fairness guarantees for neural networks
de réir: Benussi, E, et al.
Foilsithe / Cruthaithe: (2022)

Robust load forecasting towards adversarial attacks via Bayesian learning
de réir: Zhou, Y, et al.
Foilsithe / Cruthaithe: (2022)

On the adversarial robustness of Bayesian machine learning models
de réir: Blaas, AC
Foilsithe / Cruthaithe: (2021)

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
de réir: Laurenti, L, et al.
Foilsithe / Cruthaithe: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
de réir: Laurenti, L, et al.
Foilsithe / Cruthaithe: (2017)

Time Series Forecasting with Missing Data Using Generative Adversarial Networks and Bayesian Inference
de réir: Xiaoou Li
Foilsithe / Cruthaithe: (2024-04-01)

Adversarially Robust Fault Zone Prediction in Smart Grids With Bayesian Neural Networks
de réir: Emad Efatinasab, et al.
Foilsithe / Cruthaithe: (2024-01-01)

Trustworthiness and certified robustness for deep learning
de réir: Xia, Song
Foilsithe / Cruthaithe: (2022)

Certifiable Outlier-Robust Geometric Perception
de réir: Yang, Heng
Foilsithe / Cruthaithe: (2023)

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

Certifiers make neural networks vulnerable to availability attacks
de réir: Lorenz, T, et al.
Foilsithe / Cruthaithe: (2023)

Robust simulation-based inference in cosmology with Bayesian neural networks
de réir: Pablo Lemos, et al.
Foilsithe / Cruthaithe: (2023-01-01)

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

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

AutoBayes: Automated Bayesian Graph Exploration for Nuisance- Robust Inference
de réir: Andac Demir, et al.
Foilsithe / Cruthaithe: (2021-01-01)

Adversarial attacks and adversarial robustness in computational pathology
de réir: Narmin Ghaffari Laleh, et al.
Foilsithe / Cruthaithe: (2022-09-01)

Towards Fast computation of certified robustness for ReLU networks
de réir: Weng, Tsui-Wei, et al.
Foilsithe / Cruthaithe: (2021)

ME-Net: Towards effective adversarial robustness with matrix estimation
de réir: Yang, Y, et al.
Foilsithe / Cruthaithe: (2021)

Bayesian inference in FMRI.
de réir: Woolrich, M
Foilsithe / Cruthaithe: (2012)

Bayesian inference in FMRI
de réir: Woolrich, M
Foilsithe / Cruthaithe: (2012)

On the adversarial robustness of aerial detection
de réir: Yuwei Chen, et al.
Foilsithe / Cruthaithe: (2024-11-01)

Multivariate Financial Time-Series Prediction With Certified Robustness
de réir: Hui Li, et al.
Foilsithe / Cruthaithe: (2020-01-01)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
de réir: Wijk, H, et al.
Foilsithe / Cruthaithe: (2022)

Manifold-driven decomposition for adversarial robustness
de réir: Wenjia Zhang, et al.
Foilsithe / Cruthaithe: (2024-01-01)

The R Package MitISEM: Efficient and Robust Simulation Procedures for Bayesian Inference
de réir: Nalan Baştürk, et al.
Foilsithe / Cruthaithe: (2017-07-01)