avatar

Sayanton Dibbo

Incoming Assistant Professor
The University of Alabama
sdibbo (at) ua.edu


About Me

I am Sayanton Dibbo, an incoming Assistant Professor in the CS department at the University of Alabama. I have received my Ph.D. in CS from the Dartmouth College. Prior to that, I have worked on AI/ML and Security/Privacy with Los Alamos National Laboratory (LANL) and Financial Regulatory Authority (FINRA). Before joining Dartmouth, I received my MS in CS from the University of California, Riverside.

My research interests span the areas of Deep Learning, Computer Vision, and Secure & Trustworthy AI/ML modeling. I’m exploring (1) analyzing data-driven AI/ML systems, including foundation models (e.g., LLMs and Multimodal systems), and (2) focusing on security and privacy aspects of the data involved in traditional ML as well as foundational models to investigate attacks (adversarial and privacy) and develop novel defense techniques to enhance robustness. My research spans various data modalities, including images, tabular, audio, and text data.

In my free time, I love to travel to new places.

I will join as an Assistant Professor in CS at the University of Alabama in Fall 2025. You are welcome to email me (sdibbo@ua.edu) with the subject line "Prospective AI/ML/Cyber Student" along with your CV, Transcript, and GRE scores if you want to work with me.

Research Interests

Education

Appointments

News

Publications

  1. ECCV
    Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
    Sayanton Dibbo, Adam Breuer, Juston Moore, Michael Teti
    The 18th European Conference on Computer Vision (ECCV), 2024.
    PDF arXiV Project Page BibTex Published

  2. ICASSPW
    LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition
    Sayanton Dibbo, Juston Moore, Garrett Kenyon, Michael Teti
    IEEE International Conference on Acoustics, Speech and Signal Processing Workshops (ICASSPW), 2024.
    PDF arXiV Project Page BibTex Published

  3. CSF
    SoK: Model Inversion Attack Landscape: Taxonomy, Challenges, and Future Roadmap
    Sayanton Dibbo
    IEEE 36th Computer Security Foundations Symposium (CSF), 2023.
    PDF BibTex Slides Published

  4. AdvML
    How Can Neuroscience Help Us Build More Robust Deep Neural Networks?
    Sayanton Dibbo, Siddharth Mansingh, Jocelyn Rego, Garrett Kenyon, Juston Moore, Michael Teti
    ICML Workshop on Adversarial Machine Learning (AdvML), 2023.
    PDF BibTex Video Published

  5. TDSC
    Bag of on-phone ANNs to secure IoT objects using wearable and smartphone biometrics
    Sudip Vhaduri, William Cheung, Sayanton Dibbo
    IEEE Transactions on Dependable and Secure Computing (TDSC), 2023.
    PDF BibTex Published

  6. SaTML
    Model Inversion Attack with Least Information and an In-depth Analysis of its Disparate Vulnerability
    Sayanton Dibbo, Dae Lim Chung, Shagufta Mehnaz
    IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2023.
    PDF BibTex Video Published

  7. USENIX
    Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models
    Shagufta Mehnaz, Sayanton Dibbo, Ehsanul Kabir, Ninghui Li, Elisa Bertino
    31st USENIX Security Symposium (USENIX Security), 2022.
    PDF arXiV BibTex Video Published

  8. SaSeIoT
    On-phone CNN model-based implicit authentication to secure IoT wearables
    Sayanton Dibbo, William Cheung, Sudip Vhaduri
    The 5th International Conference on Safety and Security with IoT (SaSeIoT), 2022.
    PDF arXiV BibTex Best Presentation

Services

Conference/Journal Reviewers