Sijia Liu

39

Papers

316

Total Citations

Papers (39)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

ID-Patch: Robust ID Association for Group Photo Personalization

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection

Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

Proactive Image Manipulation Detection

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Adversarial Robustness vs. Model Compression, or Both?

On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method

RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions

Adversarial T-shirt! Evading Person Detectors in A Physical World

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

Higher-Order Certification For Randomized Smoothing

Training Stronger Baselines for Learning to Optimize

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

Adversarial Attack Generation Empowered by Min-Max Optimization

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?

Advancing Model Pruning via Bi-level Optimization

Fairness Reprogramming

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Model Sparsity Can Simplify Machine Unlearning

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications