Trustworthy AI

On Large Language Models' Hallucination with Regard to Known Facts
Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon …
PDF 引用
On Large Language Models' Hallucination with Regard to Known Facts
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
The rise of generative neural networks has triggered an increased demand for intellectual property (IP) protection in generated …
PDF 引用
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
Improving Robustness of Intent Detection Under Adversarial Attacks: A Geometric Constraint Perspective
Deep neural networks (DNNs)-based natural lan- guage processing (NLP) systems are vulnerable to being fooled by adversarial examples …
PDF 引用
Improving Robustness of Intent Detection Under Adversarial Attacks: A Geometric Constraint Perspective
Trustworthy AI: From Principles to Practices
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, …
PDF 引用
Trustworthy AI: From Principles to Practices