Summary
Viet Vo is a postdoctoral researcher based in Adelaide with nine years of experience bridging machine learning and security, specializing in adversarial robustness and trustworthy AI. After completing a PhD at the University of Adelaide, he produced multiple state-of-the-art black-box adversarial attacks (SparseEvo, BlockDescent, Brusli) published at venues including ICLR and NDSS, demonstrating both theoretical insight and practical query efficiency gains. He now works on safe and responsible AI and LLM robustness at the Australian Institute for Machine Learning, translating academic advances into applied AI safety research. Viet’s background in high-volume manufacturing engineering at Intel gives him a rare systems-and-process perspective that informs his empirical rigor and focus on reproducible, efficient attacks and defenses. He maintains project pages and reproducible toolchains for his work, reflecting a commitment to open science and deployable research.
8 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Adelaide
Master of Engineering (M.Eng.), Electronic and Computer Engineering, Master of Engineering (M.Eng.), Electronic and Computer Engineering at RMIT University Vietnam
Bachelor of Engineering (B.Eng.), Electrical and Electronics Engineering, Bachelor of Engineering (B.Eng.), Electrical and Electronics Engineering at Ho Chi Minh City University of Technology
Le Hong Phong High School For The Gifted, HCMC, Vietnam
English