Hassan Ali
PhD Candidate, UNSW

I am a Ph.D. candidate in Computer Science and Engineering (CSE) at the University of New South Wales (UNSW), Sydney. I am supervised by Dr. Salil Kanhere, Dr. Sanjay Jha and Dr. Surya Nepal.

My research interests are diverse.

My past research work has largely focused on the trustworthy Machine Learning (ML) algorithms, particularly Deep Neural Networks (DNNs), where the trustworthiness refers to the adversarial robustness, security, privacy, interpretability, alignment and fairness of DNNs.

I can be contacted at: hassan.ali@unsw.edu.au

News:

Selected Works:

  1. Robust Encrypted Inference in Deep Learning: A Pathway to Secure Misinformation Detection
    Hassan Ali*, Rana Tallal Javed*, Adnan Qayyum, Amer AlGhadhban, Meshari Alazmi, Ahmad Alzamil, Khaled Al-utaibi, and Junaid Qadir (*equal contribution)
    IEEE Transactions on Dependable and Secure Computing (2024).
    Links: [Paper] [Code]

  2. R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild
    Muhammad Atif Butt, Hassan Ali, Adnan Qayyum, Waqas Sultani, Ala Al-Fuqaha, and Junaid Qadir
    International Journal of Computer Vision (2024).
    Links: [Paper] [Code]

  3. Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models
    Hassan Ali, Muhammad Atif Butt, Fethi Filali, Ala Al-Fuqaha, and Junaid Qadir
    IEEE Transactions on Intelligent Transportation Systems (2023).
    Links: [Paper] [Code]

  4. Con-detect: Detecting adversarially perturbed natural language inputs to deep classifiers through holistic analysis
    Hassan Ali*, Muhammad Suleman Khan*, Amer AlGhadhban, Meshari Alazmi, Ahmad Alzamil, Khaled AlUtaibi, and Junaid Qadir (*equal contribution)
    Computers & Security 132 (2023): 103367.
    Links: [Paper] [Code]

  5. Tamp-X: Attacking explainable natural language classifiers through tampered activations
    Hassan Ali*, Muhammad Suleman Khan*, Ala Al-Fuqaha, and Junaid Qadir (*equal contribution)
    Computers & Security 120 (2022): 102791.
    Links: [Paper] [Code]

  6. Fadec: A fast decision-based attack for adversarial machine learning
    Faiq Khalid*, Hassan Ali*, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, and Muhammad Shafique (*equal contribution)
    In 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1-8. IEEE, 2020.
    Links: [Paper] [Code]