Learning to poison large language models for downstream manipulation
Hijacking Large Language Models via Adversarial In-Context Learning
This work introduces a novel transferable attack against In-Context-Learning to hijack LLMs to generate the target response or jailbreak. We also propose a defense strategy …
An example preprint / working paper
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.