Publications

2025

1. PAKDD

   

   Defense Against Multi-target Multi-trigger Backdoor Attacks

   Haripriya Harikumar, Santu Rana, Kien Do, and 4 more authors

   2025
2. SaTML

   Targeted Manifold Manipulation Against Adversarial Attack

   Banibrata Ghosh, Haripriya Harikumar, Santu Rana, and 1 more author

   In , 2025
3. arXiv preprint

   Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation

   Banibrata Ghosh, Haripriya Harikumar, Santu Rana, and 1 more author

   In , 2025
4. arXiv preprint

   

   TRUST: Test-time Resource Utilization for Superior Trustworthiness

   Haripriya Harikumar and Santu Rana

   2025

   HTML
5. UAI

   

   Privacy-Preserving Neural Processes for Probabilistic User Modeling

   Amir Sonee^*, Haripriya Harikumar^*, Alex Hämäläinen, and 2 more authors

   2025

   Abs Code

   Uncertainty-aware user modeling is crucial for designing AI systems that adapt to users in real-time while addressing privacy concerns. This paper proposes a novel framework for privacy-preserving probabilistic user modeling that integrates uncertainty quantification and differential privacy (DP). Building on neural processes (NPs), a scalable latent variable probabilistic model, we enable meta-learning for user behaviour prediction under privacy constraints. By employing differentially private stochastic gradient descent (DP-SGD), our method achieves rigorous privacy guarantees while preserving predictive accuracy. Unlike prior work, which primarily addresses privacy-preserving learning for convex or smooth functions, we establish theoretical guarantees for non-convex objectives, focusing on the utility-privacy trade-offs inherent in uncertainty-aware models. Through extensive experiments, we demonstrate that our approach achieves competitive accuracy under stringent privacy budgets. Our results showcase the potential of privacy-preserving probabilistic user models to enable trustworthy AI systems in real-world interactive applications.

2024

1. FGVC-CVPR

   Composite Concept Extraction through Backdooring

   Banibrata Ghosh^*, Haripriya Harikumar^*, Khoa Doan, and 2 more authors

   In Fine Grained VIsual Categorization Workshop at CVPR, 2024
2. ICPR

   

   Composite Concept Extraction through Backdooring

   Banibrata Ghosh^*, Haripriya Harikumar^*, Khoa Doan, and 2 more authors

   In , 2024

   Abs HTML

   Learning composite concepts, such as "red car", from individual examples—like a white car representing the concept of "car" and a red strawberry representing the concept of "red"—is inherently challenging. This paper introduces a novel method called Composite Concept Extractor (CoCE), which leverages techniques from traditional backdoor attacks to learn these composite concepts in a zeroshot setting, requiring only examples of individual concepts. By repurposing the trigger-based model backdooring mechanism, we create a strategic distortion in the manifold of the target object (e.g., "car") induced by example objects with the target property (e.g., "red") from objects "red strawberry", ensuring the distortion selectively affects the target objects with the target property. Contrastive learning is then employed to further refine this distortion, and a method is formulated for detecting objects that are influenced by the distortion. Extensive experiments with in-depth analysis across different datasets demonstrate the utility and applicability of our proposed approach.

3. ECAI

   Revisiting the Dataset Bias Problem from a Statistical Perspective

   Kien Do, Dung Nguyen, Hung Le, and 6 more authors

   2024

2022

1. JDSA

   

   Prescriptive analytics with differential privacy

   Haripriya Harikumar, Santu Rana, Sunil Gupta, and 3 more authors

   International Journal of Data Science and Analytics, 2022
2. ECCV

   

   Towards Effective and Robust Neural Trojan Defenses via Input Filtering

   Kien Do, Haripriya Harikumar, Hung Le, and 6 more authors

   In European Conference on Computer Vision, 2022
3. NeurIPS

   Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

   Kien Do, Thai Hung Le, Dung Nguyen, and 5 more authors

   Advances in Neural Information Processing Systems, 2022

2021

1. BioData Mining

   Personalized single-cell networks: a framework to predict the response of any gene to any drug for any patient

   Haripriya Harikumar, Thomas P Quinn, Santu Rana, and 2 more authors

   BioData Mining, 2021
2. Health Care Management

   Identification of predictors and model for predicting prolonged length of stay in dengue patients

   Md Shahid Ansari, Dinesh Jain, Haripriya Harikumar, and 4 more authors

   Health Care Management Science, 2021
3. arXiv preprint

   Semantic Host-free Trojan Attack

   Haripriya Harikumar, Kien Do, Santu Rana, and 2 more authors

   arXiv, 2021
4. ECML

   

   Scalable Backdoor Detection in Neural Networks

   Haripriya Harikumar, Vuong Le, Santu Rana, and 3 more authors

   In European Conference on Machine Learning and Knowledge Discovery in Databases, 2021

   Abs

   Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch. Current backdoor detection methods fail to achieve good detection performance and are computationally expensive. In this paper, we propose a novel trigger reverseengineering based approach whose computational complexity does not scale with the number of labels, and is based on a measure that is both interpretable and universal across different network and patch types. In experiments, we observe that our method achieves perfect score in separating Trojaned models from pure models, which is an improvement over the current state-of-the art method.

2018

1. PAKDD

   Prescriptive analytics through constrained Bayesian optimization

   Haripriya Harikumar, Santu Rana, Sunil Gupta, and 3 more authors

   In Pacific-Asia Conference Knowledge Discovery and Data Mining, 2018
2. ICDM

   Differentially private prescriptive analytics

   Haripriya Harikumar, Santu Rana, Sunil Gupta, and 3 more authors

   In International conference on data mining, 2018

2016

1. ADMA

   Extracting key challenges in achieving sobriety through shared subspace learning

   Haripriya Harikumar, Thin Nguyen, Santu Rana, and 3 more authors

   In Advanced Data Mining and Applications, 2016
2. ADMA

   

   Understanding behavioral differences between short and long-term drinking abstainers from social media

   Haripriya Harikumar, Thin Nguyen, Sunil Gupta, and 3 more authors

   In Advanced Data Mining and Applications, 2016