Chen, Pin-Yu
190 publications
TMLR
2025
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-Training Objective
AAAI
2025
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers
NeurIPSW
2024
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
NeurIPSW
2024
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
NeurIPSW
2024
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-Offs in LLMs
NeurIPS
2024
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation Using Generative Models
NeurIPS
2024
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
WACV
2024
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where
TMLR
2024
Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
NeurIPS
2024
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
ICML
2024
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
ICML
2024
SF-DQN: Provable Knowledge Transfer Using Successor Feature for Deep Reinforcement Learning
NeurIPS
2024
Safe LoRA: The Silver Lining of Reducing Safety Risks When Finetuning Large Language Models
NeurIPSW
2024
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
NeurIPS
2023
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
ICMLW
2023
On Robustness-Accuracy Characterization of Large Language Models Using Synthetic Datasets
NeurIPS
2023
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
NeurIPSW
2023
Transformers as Multi-Task Feature Selectors: Generalization Analysis of In-Context Learning
NeurIPSW
2023
What Improves the Generalization of Graph Transformer? a Theoretical Dive into Self-Attention and Positional Encoding
NeurIPSW
2022
An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-Driven Molecule Optimization
ICML
2022
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
ICLR
2022
How Unlabeled Data Improve Generalization in Self-Training? a One-Hidden-Layer Theoretical Analysis
NeurIPSW
2022
SynBench: Task-Agnostic Benchmarking of Pretrained Representations Using Synthetic Data
AISTATS
2021
Rate-Improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization
IJCAI
2021
Characteristic Examples: High-Robustness, Low-Transferability Fingerprinting of Neural Networks
AAAI
2021
Fake It till You Make It: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks
ICML
2021
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-Based Generative Model for Protein Design
NeurIPS
2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations
NeurIPS
2021
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
NeurIPS
2021
Why Lottery Ticket Wins? a Theoretical Perspective of Sample Complexity on Sparse Neural Networks
MLOSS
2020
AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models
ICML
2020
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-Hidden-Layer Case
AAAI
2020
Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States
NeurIPS
2020
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
AAAI
2020
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
AAAI
2020
TemPEST: Soft Template-Based Personalized EDM Subject Generation Through Collaborative Summarization
AAAI
2019
AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
AAAI
2019
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
ICML
2019
Fast Incremental Von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
NeurIPS
2018
Explanations Based on the Missing: Towards Contrastive Explanations with Pertinent Negatives