| MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic Hang Wang, Zhen Xiang, David J Miller, George Kesidis IEEE Symposium on Security & Privacy (S&P) 2024, 2024 | 19* | 2024 |
| Detecting scene-plausible perceptible backdoors in trained DNNs without access to the training set Z Xiang, DJ Miller, H Wang, G Kesidis Neural computation 33 (5), 1329-1371, 2021 | 16 | 2021 |
| Anomaly detection of adversarial examples using class-conditional generative adversarial networks H Wang, DJ Miller, G Kesidis Computers & Security 124, 102956, 2023 | 10* | 2023 |
| Revealing perceptible backdoors in DNNs, without the training set, via the maximum achievable misclassification fraction statistic Z Xiang, DJ Miller, H Wang, G Kesidis 2020 IEEE 30th International Workshop on Machine Learning for Signal …, 2020 | 8 | 2020 |
| Improved parsimonious topic modeling based on the Bayesian information criterion H Wang, D Miller Entropy 22 (3), 326, 2020 | 7 | 2020 |
| Training set cleansing of backdoor poisoning by self-supervised representation learning H Wang, S Karami, O Dia, H Ritter, E Emamjomeh-Zadeh, J Chen, ... ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 5 | 2023 |
| Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection H Wang, Z Xiang, DJ Miller, G Kesidis arXiv preprint arXiv:2308.04617, 2023 | 3 | 2023 |
| Post-Training Overfitting Mitigation in DNN Classifiers H Wang, DJ Miller, G Kesidis arXiv preprint arXiv:2309.16827, 2023 | | 2023 |
David MillerProfessor of Electrical Engineering, Penn State UniversityVerified email at psu.edu
