2 papers
cs.CR2025
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
Zhang Wei, Hanxuan Chen, Peilu Hu +19
Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suite…
cs.CL2023
TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4
Zihao Tan, Qingliang Chen, Yongjian Huang +1
Prompt-based learning has been widely applied in many low-resource NLP tasks such as few-shot scenarios. However, this paradigm has been shown to be vulnerable to backdoor attacks.…