Zhenting Wang

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

2023 · arXiv (Cornell University)

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream …

DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training

2025 · arXiv (Cornell University)

Recent advances in reinforcement learning (RL)-based post-training have led to notable improvements in large language models (LLMs), particularly in enhancing their reasoning capabilities to handle complex tasks. However, most existing methods treat the training data …