Scholar
Haripriya Harikumar
Google Scholar ID: 50ErN80AAAAJ
Research Fellow, University of Manchester, UK
Citations & Impact
Citations
190
H-index
8
i10-index
6
Publications
20
Co-authors
20
list available
Publications
Resume (English only)
Academic Achievements
- Paper “Privacy-Preserving Neural Processes for Probabilistic User Modeling” accepted to UAI 2025 (Rank A*).
- Paper “Defense Against Multi-target Multi-trigger Backdoor Attacks” accepted to PAKDD 2025.
- Paper “Targeted Manifold Manipulation Against Adversarial Attacks” accepted to IEEE SaTML 2025.
- Paper “Composite Concept Extraction through Backdooring” accepted to ICPR 2024 and CVPR 2024 Workshop on Fine-Grained Visual Categorization.
- Paper “Revisiting the Dataset Bias Problem from a Statistical Perspective” accepted to ECAI 2024.
- Paper “Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation” accepted to NeurIPS 2022.
- Paper “Towards Effective and Robust Neural Trojan Defenses via Input Filtering” accepted to ECCV 2022.
- Paper “Prescriptive analytics with differential privacy” published in International Journal of Data Science and Analytics.
- Paper “Personalized single-cell networks: a framework to predict the response of any gene to any drug for any patient” published in BioData Mining.
- First paper on Trojan defense, “Scalable Backdoor Detection in Neural Networks,” accepted to ECML 2020.
- Workshop “Backdoors in Deep Learning: The Good, the Bad, and the Ugly” accepted to NeurIPS 2023.
- Awarded ELSA travel grant to attend CISPA-ELLIS Summer School 2025 on Trustworthy AI.
- Awarded travel grant for IEEE SaTML 2025.
- Delivered talks at IEEE Student Branch, MAIL Research Lab, and FOSS-CIL T24 conference.
- Served as panelist in Black in AI Emerging Leaders Grad prep program.
- Invited mentor at Women in Machine Learning (WiML) Workshop 2023.
