0

Pin-Yu Chen

Papers
36

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
36papers

Authored papers

36

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

arXiv 2026

2026

Emergent Social Intelligence Risks in Generative Multi-Agent Systems

arXiv 2026

2026

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

arXiv 2026

2026

Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs

arXiv 2025

2025

STAR: Spectral Truncation and Rescale for Model Merging

arXiv 2025

2025

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

arXiv 2025

2025

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

arXiv 2025

2025

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

arXiv 2025

2025

Measuring the Robustness of Audio Deepfake Detectors

arXiv 2025

2025

TrustLLM: Trustworthiness in Large Language Models

arXiv 2024

2024

Attention Tracker: Detecting Prompt Injection Attacks in LLMs

arXiv 2024

2024

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

arXiv 2024

2024

Larimar: Large Language Models with Episodic Memory Control

arXiv 2024

2024

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

arXiv 2024

2024

DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection

arXiv 2024

2024

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

arXiv 2024

2024

Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models

arXiv 2024

2024

Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!

arXiv 2024

2024

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

hyporadise-an-open-baseline-for-generative

2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks

ICCV 2023 1

2023

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes

arXiv 2023

2023

Uncovering the Hidden Cost of Model Compression

arXiv 2023

2023

Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers

arXiv 2023

2023

Exploring the Benefits of Visual Prompting in Differential Privacy

ICCV 2023 1

2023

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

arXiv 2023

2023

AutoVP: An Automated Visual Prompting Framework and Benchmark

arXiv 2023

2023

Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks

arXiv 2023

2023

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models

arXiv 2023

2023

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

arXiv 2023

2023

Reprogramming Pretrained Language Models for Antibody Sequence Infilling

arXiv 2022

2022

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

arXiv 2022

2022

Visual Prompting for Adversarial Robustness

arXiv 2022

2022

Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration

arXiv 2022

2022

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

ICCV 2023 1

2022

Auto-Transfer: Learning to Route Transferrable Representations

arXiv 2022

2022

Vision Transformers are Robust Learners

arXiv 2021

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 36 papers