Pin-Yu Chen

53

Papers

245

Total Citations

Papers (53)

Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers

PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection

Large Language Models can Become Strong Self-Detoxifiers

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

How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?

Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

Larimar: Large Language Models with Episodic Memory Control

What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks

Position: TrustLLM: Trustworthiness in Large Language Models

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

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations

How to Backdoor Diffusion Models?

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

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

Exploring the Benefits of Visual Prompting in Differential Privacy

Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification

Robust Mixture-of-Expert Training for Convolutional Neural Networks

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

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

A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness

How Robust Are Randomized Smoothing Based Defenses to Data Poisoning?

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

Overload: Latency Attacks on Object Detection for Edge Devices

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

Efficient Neural Network Robustness Certification with General Activation Functions

Higher-Order Certification For Randomized Smoothing

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

Optimizing Mode Connectivity via Neuron Alignment

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

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

Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination

Adversarial Attack Generation Empowered by Min-Max Optimization

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations

Predicting Deep Neural Network Generalization with Perturbation Response Curves

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

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis

Uncovering and Quantifying Social Biases in Code Generation

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

RADAR: Robust AI-Text Detection via Adversarial Learning

HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

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

PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach