Pin‐Yu Chen

AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks

2019 · 364 Zit. · Proceedings of the AAAI Conference on Artificial Intelligence

Efficient Neural Network Robustness Certification with General Activation Functions

2018 · 172 Zit. · DSpace@MIT (Massachusetts Institute of Technology)

TrustLLM: Trustworthiness in Large Language Models

2024 · 50 Zit. · arXiv (Cornell University)

AI Explainability 360 Toolkit

2020 · 33 Zit.

AI Explainability 360: Impact and Design

2022 · 17 Zit. · Proceedings of the AAAI Conference on Artificial Intelligence

Locally Differentially Private Document Generation Using Zero Shot Prompting

2023 · 13 Zit.

Reprogrammable-FL: Improving Utility-Privacy Tradeoff in Federated Learning via Model Reprogramming

2023 · 6 Zit.

Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records

2021 · 2 Zit. · arXiv (Cornell University)

Trustworthiness Evaluation of Large Language Models

2025 · 1 Zit.

AI Risk Management Should Incorporate Both Safety and Security

2024 · 1 Zit. · arXiv (Cornell University)

AI Explainability 360: Impact and Design

2021 · 1 Zit. · arXiv (Cornell University)

ICX360: In-Context eXplainability 360 Toolkit

2025 · 0 Zit. · ArXiv.org

Editorial: Safe and Trustworthy Machine Learning

2021 · 0 Zit. · Frontiers in Big Data

Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models

2024 · 0 Zit.

Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models

2025 · 0 Zit. · ArXiv.org