Ngoc N. Tran's homepage

Profile

Computer Science PhD student at Vanderbilt University. Adversarial machine learning researcher. Curious about everything. Skillful at team-working and collaborating. Creative and persistent. Keen on self-learning. Passionate about sharing knowledge. CTF enthusiast.

Education

PhD Student, Computer Science GPA: 4.00/4.00

Expected May 2028

Topic: Artificial Intelligence Security

Vanderbilt University, Nashville, TN

+ Notable courses taken:

Principles of Computer Security Research
Project in Data-Centric AI
Special Topics in Deep Learning
Advanced Artificial Intelligence
Advanced Machine Learning

Master of Science, Computer Science GPA: 4.00/4.00

May 2021

Topic: Adversarial Machine Learning

Rensselaer Polytechnic Institute, Troy, NY

+ Notable courses taken:

Machine Learning from Data
Cryptography and Network Security I
Computer Operating Systems
Analysis of Algorithms
Large Scale Matrix Computation and Machine Learning
Computational Finance
Programming Languages

B.A. Pure/Computational Mathematics GPA: 3.74/4.00

May 2017

Minor(s): Computer Science

Summa Cum Laude

Wabash College, Crawfordsville, IN

+ Notable courses taken:

Linear Algebra
Abstract Algebra
Numerical Analysis
Real Analysis
Elementary and Partial Differential Equations
Complex Analysis
Computer Algebra
Combinatorics
Operations Research
Theory of Numbers

Experience

Teaching Assistant, Computer Science Department

Vanderbilt University, Nashville, TN

2023 - Present

Held office hours, answered forum questions, and graded assignments for assigned classes

CS 3250: Algorithms
CS 4278: Principles of Software Engineering
CS 8395: Special Topics in Computer Security Research
CS 3270: Programming Languages

Research Resident, AI Residency Program

VinAI Research, Hanoi, Vietnam

2021 - 2023

Conducted research in the field of Machine Learning
Participated in weekly meetings of the Machine Learning reading group
Supported as speaker at various AI-centric events
Developed internal projects for VinFast and VinHomes
Attended courses relevant to research interests

AI Research Team Lead, R&D Department

Sun-Asterisk Inc., Hanoi, Vietnam

2019 - 2021

Research Lead: Managed research team, organized internal knowledge sharing seminars, submitted conference papers, supported other product teams. Lead a team of 10.
Project Lead: Stabo - an internal meeting room scheduler bot. Lead a team of 5.
Teacher/Lecturer: Taught the Machine Learning Fundamentals course, a joint project of Sun* Inc. and AOTS, Japan. Held seminars at universities and venues.

Grad Teaching & Learning Assistant, Advising & Learning Assistance Center

Rensselaer Polytechnic Institute, Troy, NY

Spring 2019

Held office hours and exam review sessions for assigned classes

CSCI-1100: Introduction to Computer Science
CSCI-1200: Data Structures

Teaching Assistant, Computer Science Department

Rensselaer Polytechnic Institute, Troy, NY

2017-2019

Head Teaching Assistant for CSCI-1100: Introduction to Computer Science

Taught lab sessions, held office hours, answered forum questions, graded assignments

Grading for CSCI-2500: Computational Organization and CSCI-4210: Operating Systems

Research Assistant, Computer Science Department

Rensselaer Polytechnic Institute, Troy, NY

Summer 2018

Reviewed existing literature over matrix completion from limited observations
Worked on matrix sketching conditions under the supervision of Dr. Alex Gittens

Research Assistant, Mathematics Department

Coe College, Cedar Rapids, IA

Summer 2016

Researched on the patterns of ABC Endview puzzles
Discovered a Fibonacci-like pattern in minimal-clue conditions

Helpdesk Intern, IT Service

Wabash College, Crawfordsville, IN

2015-2016

Managed installation and maintenance of Wabash College's facility
Troubleshot and resolved technical problems from faculty and students

Junior Dev Intern, FPT Software

FPT Corporation, Hanoi, Vietnam

Summer 2014

Java Trainee: prepared for the OCJP test, a mandatory requirement for the employees
Learned the outsourcing and workload aspects from the DIRECTV project

Publications & Manuscripts Asterisk (*) denotes equal contribution.

Improving Routing in Sparse Mixture of Experts with Graph of Tokens

Tam Minh Nguyen, Ngoc N. Tran, Khai Nguyen, Richard Baraniuk

Preprint | Code

We stablize Mixture-of-Expert assignment fluctuations during training using information from token computation graphs. Under review.

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective

Hoang Phan, Lam Tran, Quyen Tran, Ngoc N. Tran, Tuan Truong, Qi Lei, Nhat Ho, Dinh Phung, Trung Le

Preprint | Code

We leverage multiple loss formulations to enhance model generalization ability in multi-task learning. Under review.

Generalization Bounds for Robust Contrastive Learning: From Theory to Practice

Ngoc N. Tran*, Tung Lam Tran*, Anh Tuan Bui, Tung Pham, Toan Tran, Dinh Phung, Trung Le

Preprint | Code

We identify which components in the unsupervised training process can improve the robust supervised loss. Under review.

PBP: Post-training Backdoor Purification for Malware Classifiers

Dung Thuy Nguyen, Ngoc N. Tran, Taylor T. Johnson, Kevin Leach

Preprint | Proceedings | Code

We leverage batch statistics during finetuning to purify backdoored malware classifiers with limited data. NDSS 2025.

Anti-DreamBooth: Protecting Users From Personalized Text-to-Image Synthesis

Thanh Van Le*, Hao Phung*, Thuan Hoang Nguyen*, Quan Dao*, Ngoc N. Tran, Anh Tran

Preprint | Proceedings | Code | Website

We propose adding imperceptible patterns to public images to void them from fine-tuning diffusion models. ICCV 2023.

Sharpness & Shift-Aware Self-Supervised Learning

Ngoc N. Tran, Son Duong, Hoang Phan, Tung Pham, Dinh Phung, Trung Le

Preprint | Code

We enhance SimCLR by minimizing loss sharpness and improving the practical positive-pair distribution. arXiv 2023.

Stochastic Multiple Target Sampling Gradient Descent

Hoang Viet Phan, Ngoc N. Tran, Trung Le, Toan Tran, Nhat Ho, Dinh Phung

Preprint | Proceedings | Code | Poster

We propose MT-SGD, allowing us to sample from the joint high-likelihood of multiple target distributions. NeurIPS 2022.

Multiple Perturbation Attack: Attack Pixelwise Under Mixed Lp-norms For Better Adversarial Performance

Ngoc N. Tran, Anh Bui, Dinh Phung, Trung Le

Preprint | Code | Poster

We propose combining perturbations under different norms for a more effective yet imperceptible attack. arXiv 2022.

ReINTEL Challenge 2020: A Comparative Study of Hybrid Deep Neural Network for Reliable Intelligence Identification on Vietnamese SNSs

Hoang Viet Trinh, Tung Tien Bui, Tam Minh Nguyen, Huy Quang Dao, Quang Huu Pham, Ngoc N. Tran, Ta Minh Thanh

Preprint | Proceedings

We propose a multimodal model leveraging both tabular metadata and text content for fake news detection. VLSP 2020.

Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices

Toan Pham Van, Ngoc N. Tran, Hoang Pham Minh, Tam Nguyen Minh, Thanh Ta Minh

Preprint | Proceedings | Slides

We proposed an efficient system for model version management and licensing for edge-device deployment. CIIS 2020.

From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection

Quang Huu Pham, Viet Anh Nguyen, Linh Bao Doan, Ngoc N. Tran, Thanh Ta Minh

Preprint | Proceedings | Slides

We fine-tuned PhoBERT for Hate Speech Detection using various training techniques. Best Paper Award, IEEE KSE 2020.

Interpreting the Latent Space of Generative Adversarial Networks using Supervised Learning

Toan Pham Van, Tam Minh Nguyen, Ngoc N. Tran, Hoai Viet Nguyen, Linh Bao Doan, Huy Quang Dao, Thanh Ta Minh

Preprint | Proceedings | Slides | Presentation

We used orthogonality constraints as regularization to enforce independent and interpretable embeddings. ACOMP 2020.

Efficient Palm-Line Segmentation with U-Net Context Fusion Module

Toan Pham Van, Son Trung Nguyen, Linh Bao Doan, Ngoc N. Tran, Ta Minh Thanh

Preprint | Proceedings | Slides

We built a U-Net model with our custom Context Fusion Module to extract palm lines from hand images. ACOMP 2020.

Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music

Toan Pham Van, Ngoc Tran Ngo Quang, Ta Minh Thanh

Preprint | Proceedings | Slides

We applied vocal segment detection, extraction, and a classifier to the singer voice classification problem. SoICT 2019.

Deep Neural Networks Based Invisible Steganography for Audio-into-Image Algorithm

Quang Pham Huu, Thoi Hoang Dinh, Ngoc N. Tran, Toan Pham Van, Thanh Ta Minh

Preprint | Proceedings | Slides

We proposed a new approach of employing deep learning in hide secret audio in a cover image. IEEE GCCE 2019.

Projects

HopSkipJumpAttack Reimplementation

Sun-Asterisk Inc., Hanoi, Vietnam

https://github.com/ngoctnq/hopskipjumpattack

June 2020

This project is a reimplementation of Chen et. al black-box decision-based attack on deep learning models. Wrote a post explaining the paper. Created a related AI-centered CTF challenge.

voxtrac - vocal extractor

Sun-Asterisk Inc., Hanoi, Vietnam

https://sun-asterisk.ai/poc-demo/music-separation

Fall 2019

This project implements an experimental deep model for extracting the vocal track from a master track. Incorporated into our SoICT 2019 paper.

Audio Steganography

Sun-Asterisk Inc., Hanoi, Vietnam

https://sun-asterisk.ai/poc-demo/audio-steganography

Summer 2019

This project is composed of deep learning models that are trained to embed a secret voice audio onto a cover image, or recover one from an image carrier, respectively. Results from our IEEE GCCE 2019 paper.

Cryptographic Filematcher

Rensselaer Polytechnic Institute, Troy, NY

https://github.com/ngoctnq/cryptographic-filematcher

Fall 2017

This project implements a secure method of matching two people's lists of files and finding the ones they have in common without exposing any details about the rest, using the Paillier Cryptosystem and a secure hash function.

Oral Comprehensive Assigning Tool

Wabash College, Crawfordsville, IN

https://github.com/ngoctnq/Oral-Comps-Assigning-Tool

Spring 2017

This project models the problem of assigning date/time, location, and board of professor for each senior student as a massive quasilinear programming problem, then solve it using AMPL/CPLEX.

ABC Endview

Coe College, Cedar Rapids, IA

https://github.com/ngoctnq/ABC-End-View

Spring 2016

This project does natural deductions on given puzzles and bruteforce all solutions when needed. The user can try different initial states of the board and get the corresponding possible solutions, aiding the research.

Ngoc Ngo Quang Tran

hi [at] ngoc [dot] io