Bye Bye Bye...: Evolution of repeated token attacks on ChatGPT models

Bye Bye Bye...: Evolution of repeated token attacks on ChatGPT models We recently discovered a new training data extraction vulnerability involving OpenAI’s chat completion models (including GPT-3.5 and GPT-4). This work builds upon prior Dropbox LLM prompt injection research as well as that of academic researchers. Our findings were shared with OpenAI in January 2024, confirmed as vulnerabilities