I am a research scientist at Sony AI where I lead efforts on enhancing capabilities and safety of large-scale generative models, particularly multimodal models.
I received my PhD from Princeton University where I was advised by Prof. Prateek Mittal and Prof. Mung Chiang. I previously interned at Meta AI (AI Red Team) and Microsoft Research. I have been fortunate to receive Qualcomm Innovation Fellowship and the Rising Star Award in adversarial machine learning.
Publications
Finding Needles in a Haystack: A Black-Box Approach to Invisible Watermark Detection
ECCV 2024 - pdf
We propose WaterMark Detector (WMD), the first invisible watermark detection method under a black-box and annotation-free setting.
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
ICML 2024 - pdf
We consider the cost of hyperparameter optimization in differentially private learning and propose a strategy that prvoides linear scaling of hyperparameters, thus reducing the privacy cost and simultaneously achieving state-of-the-art performance across 22 benchmark tasks in CV and NLP.
Differentially Private Image Classification by Learning Priors from Random Processes
NeurIPS 2023 (spotlight) - pdf | code
We show that pre-training on data from random processes enables better performance during differentially private finetuning, while simultaneously avoiding privacy leakage associated with real pretraining images.
Extracting Training Data from Diffusion Models
USENIX Security Symposium, 2023 - pdf | video | News (1, 2, 3, 4)
This was one of the first works to demonstrate significant memorization of real-world images in web-scale text-to-image generative models (Stable Diffusion, ImageN). Our findings further motivated web-scale data deduplication in training dataset of generative models.
A Light Recipe to Train Robust Vision Transformers
SaTML 2023 - pdf | video | slides | code
Contrary to the conventional wisdom of using heavy data augmentation in ViTs, we showed that a lighter data augmentation (along with other bag-of-tricks) achieves state-of-the-art performance with ViTs adversarial training.
Generating High Fidelity Data from Low-density Regions using Diffusion Models
CVPR 2022 - pdf
Our work showed strong generalization of diffusion models in the tail of the data distribution and developed adaptive sampling techniques to generate high-fidelity samples from the tail of the data distribution.
RobustBench: A Standardized Adversarial Robustness Benchmark
NeurIPS 2021 - leaderboard | pdf | code
We develop a standardized benchmark to track progress on adversarial robustness in deep learning. Our benchmark has been highly insightful and been visited by more than 40K users.
Fast-Convergent Federated Learning
IEEE Journal on Selected Areas in Communications (J-SAC) - Series on Machine Learning for Communications and Networks 2020 - pdf
We proposed a fast-convergent federated learning algorithm, called FOLB, which improves convergence speed by an smart sampling of devices in each round.
Analyzing the Robustness of Open-World Machine Learning
ACM Workshop on Artificial Intelligence and Security (AISec) 2019 - pdf | slides | code
We demonstrate the vulnerability of open-world machine learning models to adversarial examples and proposed a defense against the open-world adversarial attacks.
Selected Open Source Repositories
Invited Talks
Academic Services
Teaching and Mentoring