Personal profile
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
-
SDG 3 Good Health and Well-being -
SDG 16 Peace, Justice and Strong Institutions
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
EAGER: Clustering, Auto-Encoding, and Generative Modelling of 3D Object Representations for Manufacturing
Kesidis, G. (PI) & Miller, D. J. (CoPI)
5/15/24 → 4/30/27
Project: Research project
-
SBIR Phase I: Post-training deep neural networks certification against backdoor data poisoning attacks
Miller, D. J. (CoPI), Kesidis, G. (CoPI) & Li, X. (PI)
4/1/22 → 6/30/23
Project: Research project
-
TWC: Medium: Collaborative: Towards Securing Coupled Financial and Power Systems in the Next Generation Smart Grid
Kesidis, G. (PI) & Miller, D. J. (CoPI)
9/1/12 → 8/31/17
Project: Research project
-
NetSE Small: Unsupervised flow-based clustering
Kesidis, G. (PI) & Miller, D. J. (CoPI)
9/1/09 → 8/31/13
Project: Research project
-
NetSE Small: Unsupervised flow-based clustering
Kesidis, G. (PI) & Miller, D. J. (CoPI)
9/1/09 → 8/31/13
Project: Research project
-
Backdoor Inversion in Neural-Activation Space
Yang, G., Li, X., Wang, H., Kesidis, G. & Miller, D. J., 2025, 35th IEEE International Workshop on Machine Learning for Signal Processing: Signal Processing in the Age of Lorge Language Models, MLSP 2025. IEEE Computer Society, (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Correcting the distribution of batch normalization signals for Trojan mitigation
Li, X., Xiang, Z., Miller, D. J. & Kesidis, G., Jan 21 2025, In: Neurocomputing. 614, 128752.Research output: Contribution to journal › Article › peer-review
-
Maximum Margin-Based Activation Clipping for Posttraining Overfitting Mitigation in DNN Classifiers
Wang, H., Miller, D. J. & Kesidis, G., 2025, In: IEEE Transactions on Artificial Intelligence. 6, 10, p. 2840-2847 8 p.Research output: Contribution to journal › Article › peer-review
-
BIC-Based Mixture Model Defense Against Data Poisoning Attacks on Classifiers: A Comprehensive Study
Li, X., Miller, D. J., Xiang, Z. & Kesidis, G., 2024, In: IEEE Transactions on Knowledge and Data Engineering. 36, 8, p. 3697-3711 15 p.Research output: Contribution to journal › Article › peer-review
3 Scopus citations -
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection
Wang, H., Xiang, Z., Miller, D. J. & Kesidis, G., 2024, 34th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2024 - Proceedings. IEEE Computer Society, (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open Access