Yue Xing

A look at how adversarial training enhances machine learning models' robustness.

Data poisoning threatens the integrity of in-context learning systems, revealing hidden vulnerabilities.

Exploring how adversarial training improves model robustness through feature purification.

This paper analyzes the advantages of multi-head attention over single-head attention in machine learning tasks.

A look at how transformers excel with unstructured data in regression tasks.

Examining issues of memorization in AI-generated images and its implications.

Understanding the impact of adversarial attacks on machine learning models.

A new method to safeguard datasets against unauthorized usage in generative models.

A new dataset aims to improve the safety of text-to-image models against harmful content.

A new method reduces privacy risks in retrieval-augmented generation applications.

This article discusses effective knowledge checking methods in RAG systems.