I am recruiting graduate students for Spring and Fall 2022. Multiple RA positions are available in the areas of 1) adversarial deep learning, 2) ML applications in chemistry/material science, and 3) ML applications in medical data analysis.
- Our paper titled "Deep learning 2D and 3D optical sectioning microscopy using cross-modality Pix2Pix GAN image translation" was accepted for publication in Biomedical Optics Express. Well done, Joy! (Nov 2021)
- Our paper titled "Defeating Traffic Analysis via Differential Privacy:A Case Study on Streaming Traffic" was accepted for publication in International Journal of Information Security . Great job, Xiaokuan! (Nov 2021)
- Akshay Mehra will be presenting our paper titled "Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning" at the Neural Information Processing Systems (NeurIPS) 2021. The final version will be linked here soon. (Sep 2021)
- Akshay Mehra will be presenting our paper titled "Penalty Method for Inversion-Free Deep Bilevel Optimization" at the Asian Conference on Machine Learning (ACML) 2021. The final version will be uploaded here soon. (Sep 2021)
- I'm serving on the Senior Program Committee at the AAAI Conference on Artificial Intelligence 2022. (Aug 2021)
- I gave a talk on "Understanding Out-of-distribution Robustness of Machine Learning through Data Poisoning" at KAIST and KIAS (July 2021).
- Akshay Mehra will be presenting our paper titled "On the Effectiveness of Poisoning against Unsupervised Domain Adaptation" at the ICML Workshop on Adversarial Machine Learning 2021. The paper can be found here (Jul 2021).
- I gave a talk on "Data poisoning attack on certifiably robust classifiers" at the LATech's ECE seminar (May 2021).
- The prospect of AI's impact from our faculty's point of view was recently featured in Tulanian.
- Welcome Kiran Shrestha to the Machine Learning Group !!!
- Riley Juenemann (co-advised by Scott McKinley who is the primary) will be pursuing her PhD at Stanford University with the prestigious NSF Graduate Research Fellowship. She also received the William Wallace Peery Medal for Academic Excellence. Congratulations!!!
- Caroline Mayberry and Samantha Rothman will be presenting our work on "A Machine Learning Exploration of Early Handwriting Development" at the Association for Psychological Science (APS) 2021 Virtual Convention. The poster and the paper will be released soon. (May 2021)
- I gave a short presentation on "ML predictions of mixing enthalpy of complex alloys " at 2021 LAMDA Technical Conference (Apr 2021).
- Akshay Mehra will be presenting our paper titled "How Robust are Randomized Smoothing based Defenses to Data Poisoning?" at the Computer Vision and Pattern Recognition (CVPR) 2021. The paper can be found here. (June 2021)
- Chanho Lim will be presenting our current work on "Machine Learning Approaches in Digital Health" at the 14th Annual Western Afib Symposium. (Feb 2021)
- I gave a tutorial talk on Adversarial Machine Learning (slides are here) at the Pattern Recognition and Machine Learning Winter School 2021. (Feb 2021)
- Byunggill Joe will be presenting "Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks" at the AAAI 2021 Workshop on Trustworthy AI for Healthcare. (Feb 2021)
- Akshay Mehra will be presenting "Stealthy Poisoning Attack on Certified Robustness" at the NeurIPS'20 Workshop on Dataset Curation and Security. There is also the poster and the full arXiv version. (Dec 2020)
- I'm the Tulane lead of the Louisiana Material Design Alliance (LAMDA). We have recently been awared $20 milion NSF RII grant.
All aspects of Machine Learning. Specific topics include the following:
- Foundations of Deep Learning
- Adversarial Learning and Optimization
- Private and Secure Machine Learning
- Medical Image Analysis and Computational Anatomy
- Nonlinear Dimensionality Reduction and Manifold Learning
You can find the list of publications from Google scholar.