Publications

^* Equal contribution

2026

The Quantization Benefits of Residual-Free Transformers

Yiping Ji^*, Mahalakshmi Sabanayagam^*, Peyman Moghadam, Hemanth Saratchandran, Simon Lucey

NeurIPS 2026 Paper

Robustness Certificates for Neural Networks against Data Poisoning and Evasion Attacks

Sara Taheri, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Majid Zamani

IEEE OJCS 2026 Paper

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning

Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann

Trustworthy AI @ ICLR 2026 Spotlight · top 6.4% Paper Poster

2025

Exact Certification of (Graph) Neural Networks Against Label Poisoning

Mahalakshmi Sabanayagam^*, Lukas Gosch^*, Stephan Günnemann, Debarghya Ghoshdastidar

ICLR 2025 Spotlight · top 5.1% Paper Poster Code

VerifAI @ ICLR 2025 Oral

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoors

Lukas Gosch^*, Mahalakshmi Sabanayagam^*, Debarghya Ghoshdastidar, Stephan Günnemann

TMLR 2025 Paper Video Code

AdvML Frontiers @ NeurIPS 2024 Best Paper Award Oral

2024

Kernels, Data & Physics

Francesco Cagnetta, Deborah Oliveira, Mahalakshmi Sabanayagam, Nikolaos Tsilivis, Julia Kempe

JSTAT 2024 Paper

Robust Features Inference: A Test-time Defense using Spectral Projections

Anurag Singh^*, Mahalakshmi Sabanayagam^*, Krikamol Muandet, Debarghya Ghoshdastidar

TMLR 2024 Paper Poster Code

2023

Unveiling the Hessian's Connection to the Decision Boundary

Mahalakshmi Sabanayagam, Freya Behrens, Urte Adomaityte, Anna Dawid

M3L @ NeurIPS 2023 Paper Poster Code

Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel

Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar

TMLR 2023 Paper Poster Code

Learning on Graphs Meetup · Munich 2023

Improved Representation Learning Through Tensorized Autoencoders

Pascal Esser^*, Satyaki Mukherjee^*, Mahalakshmi Sabanayagam^*, Debarghya Ghoshdastidar

AISTATS 2023 Paper Poster Code

2022

Analysis of Graph Convolutional Networks using Neural Tangent Kernels

Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar

MLG @ ECML PKDD 2022 Paper Code

Graphon based Clustering and Testing of Networks: Algorithms and Theory

Mahalakshmi Sabanayagam, Leena Chennuru Vankadara, Debarghya Ghoshdastidar

ICLR 2022 Paper Poster Code

2019

Rough Set-based Feature Selection for Credit Risk Prediction using Weight Adjusted Boosting Ensemble Method

Sivasankar Elango, Selvi Chandran, Mahalakshmi Sabanayagam

Soft Computing 2019 Paper

2015

Cross Domain Sentiment Analysis Using Different Machine Learning Techniques

Mahalakshmi Sabanayagam, Sivasankar Elango

FANCCO 2015 Paper

Grace Hopper Celebration India 2016 Poster

Preprints

Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)

Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

Preprint Paper

Generalization Certificates for Adversarially Robust Bayesian Linear Regression

Mahalakshmi Sabanayagam, Russell Tsuchida, Cheng Soon Ong, Debarghya Ghoshdastidar

Preprint Paper