Hi, I'm Huy Phan, Ph.D. Candidate at Rutgers
Ph.D. candidate in Computer Engineering with 5+ years of expertise in Computer Vision, Generative AI, Model Compression & Efficiency, Model Adversarial Robustness, and Model Backdoor Security. Author of over 10 papers published in leading AI conferences.
Contact
Email: huyvnphan[at]gmail[dot]com
Resume: PDF File
Biography
Mr. Huy Phan is currently a Ph.D. student in Electrical and Computer Engineering (advised by Prof. Bo Yuan) at Rutgers University.
In 2018, he received his B.Sc. in Computer Science and B.Sc. in Electrical and Computer Engineering at Rutgers University. In 2020, he received his M.Sc. in Electrical and Computer Engineering, also at Rutgers University.
He was an Applied Scientist Intern at Amazon in the summer of 2023 and a Machine Learning Intern at MoMo in the summer of 2021. His research is currently focused on Energy Efficient AI and Secure AI Systems. His research topics include:
Deep Learning Adversarial Robustness (adversarial attacks and defenses).
Deep Learning Backdoor Security (backdoor attacks and backdoor defenses).
Model Compression using Low-rank tensor decomposition, Pruning, and Quantization.
Co-exploring Model Efficiency and Security.
On-device Computer Vision. Efficient DNNs for edge devices. TinyML.
Recent News
[Nov - 2023] A paper on Inaudible Backdoor Attack via Stealthy Frequency Trigger Injection in Audio Spectrogram accepted at Annual International Conference On Mobile Computing And Networking - MobiCom-24
[June - 2023] Appointed as an Applied Scientist Intern at Amazon.
[May - 2023] A paper on Security-Preserving Live 3D Video Surveillance accepted at ACM Multimedia Systems Conference - MMSys-23
[Nov - 2022] A first-author paper on Compact and Structured Deep Neural Networks with Adversarial Robustness accepted at AAAI Conference on Artificial Intelligence - AAAI-23 (Acceptance rate: 19.6%).
[Jul - 2022] A first-author paper on Robust and Imperceptible Backdoor Attacks against Compact DNN accepted at European Conference on Computer Vision - ECCV-22 (Acceptance rate: 28%).
[Jul - 2022] A paper on AI Accelerators accepted at IEEE Computer Society Annual Symposium on VLSI - ISVLSI-22.
[Jun - 2022] A paper on Audio-domain Backdoor Attack via Unnoticeable Triggers accepted at Annual International Conference On Mobile Computing And Networking - MobiCom-22 (Acceptance rate: 18%).
[Jan - 2022] A first-author paper on Invisible and Efficient Backdoor Attacks for Compressed Deep Neural Networks accepted at IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP-22.
[Mar - 2022] A paper on Visual Privacy Protection in Mobile Image Recognition Using Protective Perturbation accepted at ACM Multimedia Systems Conference - MMSys-22.
[Nov - 2021] A paper on Budget-aware Neural Network Compression Based On Tucker Decomposition accepted at the Proceedings of the AAAI Conference on Artificial Intelligence - AAAI-22 (Acceptance rate 15%).
[Sep - 2021] A paper on Channel Independence-based Pruning For Compact Neural Networks accepted at the Advances in Neural Information Processing Systems - NeurIPS-21 (Acceptance rate 26%).
[June - 2021] Appointed as a Machine Learning Intern at MoMo.
[Aug - 2020] A paper on Securing Volumetric Video Streaming via Benign Use of Adversarial Perturbation accepted at the ACM International Conference on Multimedia - MM-20.
[Feb - 2020] A first-author paper on Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator accepted at the AAAI Conference on Artificial Intelligence - AAAI-20 (Acceptance rate 20.6%).