Authors marked in blue indicate our group members, and “*” indicates equal contribution.
Jump: Preprints, Conference Papers and Journal Papers


Back to Top

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
C. Fan*, J. Liu*, A. Hero, S. Liu
arXiv Preprint

UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
Y. Zhang, Y. Zhang, Y. Yao, J. Jia, J. Liu, X. Liu, S. Liu
arXiv Preprint

From Trojan Horses to Castle Walls: Unveiling Bilateral Backdoor Effects in Diffusion Models
Z. Pan*, Y. Yao*, G. Liu, B. Shen, H. V. Zhao, R. R. Kompella, S. Liu
arXiv Preprint

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images … For Now
Y. Zhang*, J. Jia*, X. Chen, A. Chen, Y. Zhang, J. Liu, K. Ding, S. Liu
arXiv Preprint

Highlighted Conference Papers

Back to Top

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
Y. Zhang*, P. Li*, J. Hong*, J. Li, Y. Zhang, W. Zheng, P. Y. Chen, J. D. Lee, W. Yin, M. Hong, Z. Wang, S. Liu, T. Chen

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
C. Fan*, J. Liu*, Y. Zhang, E. Wong, D. Wei, S. Liu
ICLR’24 (Spotlight, acceptance rate 5%)

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
A. Chen*, Y. Zhang*, J. Jia, J. Diffenderfer, J. Liu, K. Parasyris, Y. Zhang, Z. Zhang, B. Kailkhura, S. Liu

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
S. Pal, Y. Yao, R. Wang, B. Shen, S. Liu

AutoVP: An Automated Visual Prompting Frameowrk and Benchmark
H.-Y. Tsao, L. Hsiung, P.-Y. Chen, S. Liu, T.-Y. Ho

Model Sparsity Can Simplify Machine Unlearning
J. Jia*, J. Liu*, P. Ram, Y. Yao, G. Liu, Y. Liu, P. Sharma, S. Liu
NeurIPS’23 (Spotlight, acceptance rate 3%)

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
Y. Zhang*, Y. Zhang*, A. Chen*, J. Jia, J. Liu, G. Liu, M. Hong, S. Chang, S. Liu

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with Greedy Exploration
S. Zhang, M. Wang, H. Li, M. Liu, P. Chen, S. Lu, S. Liu, K. Murugesan. S. Chaudhury

Robust Mixture-of-Expert Training for Convolutional Neural Networks
Y. Zhang, R. Cai, T. Chen, G. Zhang, H. Zhang. P. Chen, S. Chang, Z. Wang, S. Liu
ICCV’23 (Oral, acceptance rate 2%)

Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
P. Khanduri, I. Tsaknakis, Y. Zhang, J. Liu, S. Liu, J. Zhang, M. Hong

Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
M. Nowaz, R. Chowdhury, S. Zhang, M. Wang, S. Liu, P. Chen

Understanding and Improving Visual Prompting: A Label-Mapping Perspective
A. Chen, Y. Yao, P. Chen, Y. Zhang, S. Liu

Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Y. Zhang, X. Chen, J. Jia, S. Liu, K. Ding

What Is Missing in IRM Training and Evaluation? Challenges and Solutions
Y. Zhang, P. Sharma, P. Ram, M. Hong, K. R. Varshney, S. Liu

Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
S. Zhang, M. Wang, P. Chen, S. Liu, S. Lu, M. Liu

A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
H. Li, M. Wang, S. Liu, P. Chen

TextGrad: Advancing Robustness Evaluation in {NLP} by Gradient-Driven Optimization
B. Hou, J. Jia*, Y. Zhang*, G. Zhang*, Y. Zhang, S. Liu, S. Chang

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Y. Zhang*, A. K. Kamath*, Q. Wu*, Z. Fan*, W., Z. Wang, S. Chang, S. Liu, C. Hao

CLAWSAT: Towards Both Robust and Accurate Code Models
J. Jia*, S. Srikant*, T. Mitrovska, C. Gan, S. Chang, S. Liu, U-M O’Reilly

Advancing Model Pruning via Bi-level Optimization
Y. Zhang*, Y. Yao*, P. Ram, P. Zhao, T. Chen, M. Hong, Y. Wang, S. Liu

Fairness Reprogramming
G. Zhang*, Y. Zhang*, Y. Zhang, W. Fan, Q. Li, S. Liu, S. Chang

Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
G. Zhang, S. Lu, Y. Zhang*, X. Chen, P. Chen, Q. Fan, L. Martie, L. Horesh, M. Hong, and S. Liu
UAI’22 (Oral, Best Paper Runner-up Award)

Revisiting and Advancing Fast Adversarial Training through the Lens of Bi-level Optimization
Y. Zhang*, G. Zhang*, P. Khanduri, M. Hong, S. Chang, and S. Liu

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training.
T. Chen, H. Zhang, Z. Zhang, S. Chang, S. Liu, P. Chen, and Z. Wang

Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
C. Ko, J. Mohapatra, S. Liu, P. Chen, L. Daniel, and L. Weng

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
H. Li, M. Weng, S. Liu, P. Chen, and J. Xiong

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction
Y. Xie, D. Wang, P. Chen, J. Xiong, S. Liu, S. Koyejo

Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations
P. Zhao, P. Ram, S. Lu, Y. Yao, D. Bouneffouf, X. Lin, S. Liu

Proactive Image Manipulation Detection
V. Asnani, X. Yin, T. Hassner, S. Liu, X. Liu

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
T. Chen*, Z. Zhang*, Y. Zhang*, S. Chang, S. Liu, Z. Wang

Reverse Engineering of Imperceptible Adversarial Image Perturbations
Y. Gong*, Y. Yao*, Y. Li, Y. Zhang, X. Liu, X. Lin, S. Liu

How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
Y. Zhang, Y. Yao, J. Jia, J. Yi, M. Hong, S. Chang, S. Liu
ICLR’22 (Spotlight, acceptance rate 5%)

How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
S. Zhang, M. Wang, S. Liu, P.-Y. Chen, J. Xiong

Optimizer Amalgamation
T. Huang, T. Chen, S. Liu, S. Chang, L. Amini, Z. Wang

Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
P. Khanduri, H. Yang, M. Hong, J. Liu, H.T. Wai, S. Liu

Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
C. Fan, P. Ram and S. Liu
NeurIPS Workshop MetaLearn, 2021

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
X. Ma, G. Yuan, X. Shen, T. Chen, X. Chen, X. Chen, N. Liu, M. Qin, S. Liu, Z. Wang, Y. Wang.

When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
L. Fan, S. Liu, P.-Y. Chen, G. Zhang, C. Gan.

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
G. Yuan, X. Ma, W. Niu, Z. Li, Z. Kong, N. Liu, Y. Gong, Z. Zhan, C. He, Q. Jin, S. Wang, M. Qin, B. Ren, Y. Wang, S. Liu, X. Lin.
NeurIPS’21 (Spotlight, acceptance rate 3%)

Adversarial Attack Generation Empowered by Min-Max Optimization
J. Wang, T. Zhang, S. Liu, P.-Y. Chen, J. Xu, M. Fardad, B. Li.

Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks
S. Zhang, M. Wang, S. Liu, P.-Y. Chen, J. Xiong.

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
N. Liu, G. Yuan, Z. Che, X. Shen, X. Ma, Q. Jin, J. Ren, J. Tang, S. Liu, Y. Wang.

NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Z. Li, G. Yuan, W. Niu, Y. Li, P. Zhao, Y. Cai, X. Shen, Z. Zhan, Z. Kong, Q. Jin, Z. Chen, S. Liu, K. Yang, Y. Wang, B. Ren, and X. Lin.
CVPR’21 (Oral, acceptance rate 4%)

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
T. Chen, J. Frankle, S. Chang, S. Liu, Y. Zhang, M. Carbin, and Z. Wang.

Hidden Cost of Randomized Smoothing
J. Mohapatra, C.-Y. Ko, L. Weng, P.-Y. Chen, S. Liu, L. Daniel

Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization
Z. Li, P.-Y. Chen, S. Liu, S. Lu, Y. Xu

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
R. Wang, K. Xu, S. Liu, P.-Y. Chen, T.-W. Weng, C. Gan, M. Wang

Robust Overfitting May be Mitigated by Properly Learned Smoothening
T. Chen, Z. Zhang, S. Liu, S. Chang, and Z. Wang

Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
T. Chen, Z. Zhang, S. Liu, S. Chang, and Z. Wang,

Generating Adversarial Computer Programs using Optimized Obfuscations
S. Srikant, S. Liu, T. Mitrovska, S. Chang, Q. Fan, G. Zhang, U.-M. O’Reilly

Fast Training of Provably Robust Neural Networks by SingleProp
A. Boopathy, L. Weng, S. Liu, P.-Y. Chen, G. Zhang, L. Daniel

Self-Progressing Robust Training
M. Cheng, P.-Y. Chen, S. Liu, S. Chang, C.-J. Hsieh, P. Das

RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
W. Niu, M. Sun, Z. Li, J.-A. Chen, J. Guan, X. Shen, Y. Wang, S. Liu, X. Lin, B. Ren

The Lottery Ticket Hypothesis for the Pre-trained BERT Networks
T. Chen, J. Frankle, S. Chang, S. Liu, Y. Zhang, Z. Wang, M. Carbin

Training Stronger Baselines for Learning to Optimize
T. Chen, W. Zhang, J. Zhou, S. Chang, S. Liu, L. Amini, Z. Wang
NeurIPS’20 (Spotlight, acceptance rate 3%)

Higher-Order Certification for Randomized Smoothing
J. Mohapatra, C.-Y. Ko, L. Weng, P.-Y. Chen, S. Liu, L. Daniel
NeurIPS’20 (Spotlight, acceptance rate 3%)

Adversarial T-shirt! Evading Person Detectors in A Physical World
K. Xu, G. Zhang, S. Liu, Q. Fan, M. Sun, H. Chen, P.-Y. Chen, Y. Wang, X. Lin
ECCV’20 (Spotlight, acceptance rate 5%)

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
R. Wang, G. Zhang, S. Liu, P.-Y. Chen, J. Xiong, M. Wang

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
X. Ma, W. Niu, T. Zhang, S. Liu, S. Lin, H. Li, W. Wen, X. Chen, J. Tang, K. Ma, B. Ren, Y. Wang

Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
S. Zhang, M. Wang, S. Liu, P.-Y. Chen, J. Xiong

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
S. Dutta, D. Wei, H. Yueksel, P.-Y. Chen, S. Liu, K. R. Varshney

Proper Network Interpretability Helps Adversarial Robustness in Classification
A. Boopathy, S. Liu, G. Zhang, C. Liu, P.-Y. Chen, S. Chang, L. Daniel

Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
S. Liu*, S. Lu*, X. Chen*, Y. Feng*, K. Xu*, A. Al-Dujaili*, M. Hong, U.-M. O’Reilly

Adversarial Robustness: From Self-Supervised Pretraining to Fine-Tuning
T. Chen, S. Liu, S. Chang, Y. Cheng, L. Amini, Z. Wang

Towards Verifying Robustness of Neural Networks against Semantic Perturbations
J. Mohapatra, L. Weng, P.-Y. Chen, S. Liu, L. Daniel
CVPR’20 (Oral, acceptance rate 5%)

Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
M. Cheng, S. Singh, P.-Y. Chen, S. Liu, C.-J. Hsieh

An ADMM Based Framework for AutoML Pipeline Configuration
S. Liu*, P. Ram*, D. Vijaykeerthy, D. Bouneffouf, G. Bramble, H. Samulowitz, D. Wang, A. Conn, A. Gray

Towards Certificated Model Robustness Against Weight Perturbations
L. Weng*, P. Zhao*, S. Liu, P.-Y. Chen, X. Lin, L. Daniel

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
X. Chen*, S. Liu*, K. Xu*, X. Li*, X. Lin, M. Hong, D. Cox

Generation of Low Distortion Adversarial Attacks via Convex Programming
T. Zhang, S. Liu, Y. Wang, M. Fardad

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
P. Zhao, S. Liu, P.-Y. Chen, N. Hoang, K. Xu, B. Kailkhura, X. Lin

Adversarial Robustness vs. Model Compression, or Both?
S. Ye*, K. Xu*, S. Liu, H. Cheng, J.-H. Lambrechts, H. Zhang, A. Zhou, K. Ma, Y. Wang, X. Lin

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
K. Xu*, H. Chen*, S. Liu, P.-Y. Chen, T.-W. Wen, M. Hong, X. Lin

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
P.-Y. Chen, L. Wu, S. Liu, I. Rajapakse

signSGD via Zeroth-Order Oracle
S. Liu, P.-Y. Chen, X. Chen, M. Hong

Structured Adversarial Attack: Towards General Implementation and Better Interpretability
K. Xu*, S. Liu*, P. Zhao, P.-Y. Chen, H. Zhang, D. Erdogmus, Y. Wang, X. Lin

On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
X. Chen, S. Liu, R. Sun, M. Hong

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
A. Boopathy, L. Weng, P.-Y. Chen, S. Liu, L. Daniel

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks
C.-C. Tu*, P. Ting*, P.-Y. Chen*, S. Liu, H. Zhang, J. Yi, C.-J. Hsieh, S.-M. Cheng

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization
S. Liu, B. Kailkhura, P.-Y. Chen, P. Ting, S. Chang, L. Amini

Ultra-Fast Robust Compressive Sensing Based on Memristor Crossbars
S. Liu, A. Ren, Y. Wang, P. K. Varshney
ICASSP’17 (Best Student Paper Award, Third Place)

Journal Papers

Back to Top

An Introduction to Bilevel Optimization: Foundations and Applications in Signal Processing and Machine Learning
Y. Zhang, P. Khanduri, I. Tsaknakis, Y. Yao, M. Hong and S. Liu
IEEE Signal Processing Magazine, vol. 41, no. 1, pp. 38-59, Jan. 2024

Improved Linear Convergence of Training CNNs With Generalizability Guarantees: A One-Hidden-Layer Case
S. Zhang, M. Wang, J. Xiong, S. Liu, P.-Y. Chen
IEEE Transactions on Neural Networks and Learning Systems, 2020

A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
S. Liu, P.-Y. Chen, B. Kailkhura, G. Zhang, A. O. Hero, P. K. Varshney
IEEE Signal Processing Magazine, 2020

On sparse identification of complex dynamical systems: A study on discovering influential reactions in chemical reaction networks
F. Harirchi, D. Kim, O. Khalil, S. Liu, P. Elvati, M. Baranwal, A. O. Hero, A. Violi
Fuel, Elsevier, 2020

Genome Architecture Mediates Transcriptional Control of Human Myogenic Reprogramming
S. Liu, H. Chen, S. Ronquist, L. Seaman, N. Ceglia, W. Meixner, L. A. Muir, P.-Y. Chen, G. Higgins, P. Baldi, S. Smale, A. O. Hero, I. Rajapakse
iScience, Cell, 2018

Optimal Sensor Collaboration for Parameter Tracking Using Energy Harvesting Sensors
S. Zhang, S. Liu, V. Sharma, P. K. Varshney
IEEE Transactions on Signal Processing, 2018

A Memristor-Based Optimization Framework for Artificial Intelligence Applications
S. Liu, Y. Wang, M. Fardad, and P. K. Varshney
IEEE Circuits and Systems Magazine, 2018

Accelerated Distributed Dual Averaging Over Evolving Networks of Growing Connectivity
S. Liu, P.-Y. Chen, and A. O. Hero
IEEE Transactions on Signal Processing, 2018

Bias-Variance Tradeoff of Graph Laplacian Regularizer
P.-Y. Chen, S. Liu
IEEE Signal Process. Lett., 2017

Chromosome conformation and gene expression patterns differ profoundly in human fibroblasts grown in spheroids versus monolayers
H. Chen, L. Seaman, S. Liu, T. Ried, I. Rajapakse
Nucleus, 2017

Optimized Sensor Collaboration for Estimation of Temporally Correlated Parameters
S. Liu, S. Kar, M. Fardad, P. K. Varshney
IEEE Transactions on Signal Processing, 2017

Measurement Matrix Design for Compressed Detection With Secrecy Guarantees
B. Kailkhura, S. Liu, T. Wimalajeewa, P. K. Varshney
IEEE Wireless Communications Letters, 2016

Sensor Selection for Estimation with Correlated Measurement Noise
S. Liu, S. P. Chepuri, M. Fardad, E. Masazade, G. Leus, P. K. Varshney
IEEE Transactions on Signal Processing, 2016

Sparsity-Aware Sensor Collaboration for Linear Coherent Estimation
S. Liu, S. Kar, M. Fardad, and P. K. Varshney
IEEE Transactions on Signal Processing, 2015

Energy-Aware Sensor Selection in Field Reconstruction
S. Liu, A. Vempaty, M. Fardad, E. Masazade, and P. K. Varshney
IEEE Signal Processing Letters, 2014

Sensor Selection for Nonlinear Systems in Large Sensor Networks
X. Shen, S. Liu, and P. K. Varshney
IEEE Transactions on Aerospace and Electronic Systems, 2014

Optimal Periodic Sensor Scheduling in Networks of Dynamical Systems
S. Liu, M. Fardad, E. Masazade and P. K. Varshney
IEEE Transactions on Signal Processing, 2014