4 papers
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation
Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6
Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from train…
UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks
Bingyin Zhao, Yingjie Lao
Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate…
TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
Jiayu Li, Bingyin Zhao, Zilong Zhao +3
Transformers have shown impressive results in tabular data generation. However, they lack domain-specific inductive biases which are critical for preserving the intrinsic character…
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
Yuning Han, Bingyin Zhao, Rui Chu +3
Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that con…