The-Anh Ta

The-Anh Ta

About me

Hi, my name is The-Anh Ta (Tạ Thế Anh in Vietnamese). I’m a Research Scientist at The Commonwealth Scientific and Industrial Research Organisation (CSIRO), Marsfield, NSW, Australia. I do research in Applied Cryptography (Digital Signature, Zero-Knowledge Proof, Quantum-Safe Transition). Machine Learning (Neural Network Pruning, Robustness), and more recently on Energy Cybersecurity and Smart Grids.

Before moving to Australia, I was at KDDI Research, Japan; and AI Center, FPT Software, Vietnam. I obtained my PhD in Mathematics from the Paris-Saclay University, Orsay, France. Before that, I did my undergraduate studies (BSc and MSc) in Mathematics at the Eötvös Loránd University (ELTE) in Budapest, Hungary.

I grew up in Vinh Phuc (renamed to Phu Tho since 2025), Viet Nam.

My journey: Vinh Phuc → Ha Noi (Vietnam) → Budapest (Hungary) → Orsay (France) → Ho Chi Minh City (Vietnam) → Saitama (Japan) → NSW (Australia)

Recent Publications:

  1. The-Anh Ta, Xiangyu Hui, Sid Chi-Kin Chau, Ring Referral: Efficient Publicly Verifiable Ad hoc Credential Scheme with Issuer and Strong User Anonymity for Decentralized Identity and More, IEEE Symposium on Security and Privacy (IEEE SP), 2025. Paper

  2. The-Anh Ta, Sid Chi-Kin Chau, Post-Quantum Issuer-Hiding Anonymous Credential Scheme, ACM CCS Workshop on Quantum-Resistant Cryptography and Security (ACM QRSEC 2025). Paper

  3. The-Anh Ta, Sid Chau, Shangqi Lai, Relating Cyberattacks for Disrupting Electricity Spot Markets and Manipulation in Energy Derivative Markets, ACM Workshop on Cybersecurity and Privacy of Energy Systems (ACM EnergySP ‘26).

  4. Hoang Pham, The-Anh Ta, Tom Jacobs, Rebekka Burkholz, Long Tran-Thanh, The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis, The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025) Spotlight. Paper

  5. Hoang Pham, The-Anh Ta, Long Tran-Thanh, Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation, The Forty-Third International Conference on Machine Learning (ICML 2026). Paper

Visitor Map