Achievements
- 2023-July Mahum Naseer presented her paper “Scaling Model Checking for Neural Network Analysis via State-Space Reduction and Input Segmentation”, at Formal Methods for ML-enabled Autonomous Systems (FoMLAS), 2023.
- 2023-March Mahum Naseer presented her poster “Poster: Link between Bias, Node Sensitivity and Long-tail Distribution in trained DNNs”, at IEEE International Conference on Software Testing, Verification, and Validation (ICST), 2023.
- 2023-Feb Mahum Naseer published her paper “UnbiasedNets: a Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks”, in Machine Learning.
- 2022-Feb Mahum Naseer published her paper “A Formal Approach to Identifying the Impact of Noise on Neural Networks”, in Communications of the ACM.
- 2020-June Mahum Naseer presented her poster “FANNet: formal analysis of neural networks”, at Design Automation Conference (DAC), 2020.
- 2020-March Mahum Naseer presented her paper “FANNet: formal analysis of noise tolerance, training bias and input sensitivity in neural networks”, at Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020.
- 2020-Feb Mahum Naseer published her paper “Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead”, in IEEE Design & Test.
- 2019-November Mahum Naseer presented her poster “MoCTest: Model Checking and Testing based Analysis of Neural Network’s Noise Tolerance, Training Bias and Input Sensitivity” at IEEE International Workshop on Robust and Trustworthy Machine Learning (RTML), 2019.
- 2019-June Mahum Naseer presented her poster “Verifiable Robustness for Machine Learning Systems” at Design Automation Conference (DAC) 2019.