Detecting backdoor attacks on deep neural networks by activation clustering B Chen, W Carvalho, N Baracaldo, H Ludwig, B Edwards, T Lee, I Molloy, ... arXiv preprint arXiv:1811.03728, 2018 | 745 | 2018 |
Adversarial Robustness Toolbox v1. 0.0 MI Nicolae, M Sinn, MN Tran, B Buesser, A Rawat, M Wistuba, ... arXiv preprint arXiv:1807.01069, 2018 | 543 | 2018 |
Mitigating poisoning attacks on machine learning models: A data provenance based approach N Baracaldo, B Chen, H Ludwig, JA Safavi Proceedings of the 10th ACM workshop on artificial intelligence and security …, 2017 | 130 | 2017 |
Detecting poisoning attacks on machine learning in IoT environments N Baracaldo, B Chen, H Ludwig, A Safavi, R Zhang 2018 IEEE international congress on internet of things (ICIOT), 57-64, 2018 | 85 | 2018 |
Regression and causation: a critical examination of six econometrics textbooks B Chen, J Pearl Real-World Economics Review, Issue, 2013 | 62 | 2013 |
Regression and causation: a critical examination of six econometrics textbooks B Chen, J Pearl Real-World Economics Review, Issue, 2013 | 62 | 2013 |
Graphical tools for linear structural equation modeling B Chen, J Pearl Psychometrica, forthcoming, 2014 | 61 | 2014 |
Sensitivity analysis of linear structural causal models C Cinelli, D Kumor, B Chen, J Pearl, E Bareinboim International conference on machine learning, 1252-1261, 2019 | 51 | 2019 |
Using gradients to detect backdoors in neural networks W Carvalho, B Chen, BJ Edwards, T Lee, IM Molloy, J Zhang US Patent 11,132,444, 2021 | 48 | 2021 |
Testable implications of linear structural equation models B Chen, J Tian, J Pearl Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 | 41 | 2014 |
Identification and model testing in linear structural equation models using auxiliary variables B Chen, D Kumor, E Bareinboim International Conference on Machine Learning, 757-766, 2017 | 25 | 2017 |
Adversarial Robustness Toolbox v1. 0.0. arXiv 2018 MI Nicolae, M Sinn, MN Tran, B Buesser, A Rawat, M Wistuba, ... arXiv preprint arXiv:1807.01069, 0 | 24 | |
Identification and overidentification of linear structural equation models B Chen Advances in neural information processing systems 29, 2016 | 22 | 2016 |
A unifying causal framework for analyzing dataset shift-stable learning algorithms A Subbaswamy, B Chen, S Saria Journal of Causal Inference 10 (1), 64-89, 2022 | 19 | 2022 |
Incorporating knowledge into structural equation models using auxiliary variables B Chen, J Pearl, E Bareinboim Twenty-Fifth International Joint Conference on Artificial Intelligence, 3577 …, 2016 | 18 | 2016 |
Incorporating knowledge into structural equation models using auxiliary variables B Chen, J Pearl, E Bareinboim arXiv preprint arXiv:1511.02995, 2015 | 18 | 2015 |
Efficient identification in linear structural causal models with instrumental cutsets D Kumor, B Chen, E Bareinboim Advances in Neural Information Processing Systems 32, 2019 | 14 | 2019 |
Detecting and mitigating poison attacks using data provenance N Baracaldo-Angel, B Chen, E Duesterwald, HH Ludwig US Patent 11,689,566, 2023 | 13 | 2023 |
Detecting poisoning attacks on neural networks by activation clustering B Chen, W Carvalho, HH Ludwig, IM Molloy, T Lee, J Zhang, BJ Edwards US Patent 11,188,789, 2021 | 13 | 2021 |
Exogeneity and robustness B Chen, J Pearl Technical report, Tech. Rep, 2015 | 13 | 2015 |