Pin-Yu Chen
- Papers
- 36
Cite
Notes
Only stored in your browser.
Authored papers
36One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
arXiv 2026
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
arXiv 2026
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
arXiv 2026
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
arXiv 2025
STAR: Spectral Truncation and Rescale for Model Merging
arXiv 2025
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
arXiv 2025
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
arXiv 2025
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
arXiv 2025
Measuring the Robustness of Audio Deepfake Detectors
arXiv 2025
TrustLLM: Trustworthiness in Large Language Models
arXiv 2024
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
arXiv 2024
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
arXiv 2024
Larimar: Large Language Models with Episodic Memory Control
arXiv 2024
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers
arXiv 2024
DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection
arXiv 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
arXiv 2024
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
arXiv 2024
Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!
arXiv 2024
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
hyporadise-an-open-baseline-for-generative
Robust Mixture-of-Expert Training for Convolutional Neural Networks
ICCV 2023 1
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
arXiv 2023
Uncovering the Hidden Cost of Model Compression
arXiv 2023
Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers
arXiv 2023
Exploring the Benefits of Visual Prompting in Differential Privacy
ICCV 2023 1
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
arXiv 2023
AutoVP: An Automated Visual Prompting Framework and Benchmark
arXiv 2023
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
arXiv 2023
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
arXiv 2023
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
arXiv 2023
Reprogramming Pretrained Language Models for Antibody Sequence Infilling
arXiv 2022
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
arXiv 2022
Visual Prompting for Adversarial Robustness
arXiv 2022
Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
arXiv 2022
Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification
ICCV 2023 1
Auto-Transfer: Learning to Route Transferrable Representations
arXiv 2022
Vision Transformers are Robust Learners
arXiv 2021
Affiliations
Frequent co-authors
10from 36 papers