← Search

Zhiyao Ren

2 accepted papers

2025

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

ICML 2025poster

In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a critical vulnerability to backdoor attacks, where adversaries can manipulate LLM behaviors by simply poisoning a few ICL demo…

Cited by 0SourcePDFScholar
2024

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

AAAI 2024technical

Denoising Diffusion Probabilistic Models (DDPMs) have achieved significant success in generation tasks. Nevertheless, the exposure bias issue, i.e., the natural discrepancy between the training (the output of each step is calculated individually by a given input) and inference (the output of each st…

Cited by 2SourcePDFScholar