What if ChatGPT can tell you more than it should? In this video, we unveil a remarkable attack on ChatGPT that exposes its hidden training data, complete with a live demonstration. We'll look at the accompanying blog post and arXiv paper, shedding light on the intricacies of this discovery, and explain the inner workings of how and why this attack is so effective in revealing hidden information.
Blog post: not-just-memorization.github....
Paper: arxiv.org/abs/2311.17035
Discord: / discord
Prepare for the Machine Learning interview: mlexpert.io
Subscribe: bit.ly/venelin-subscribe
GitHub repository: github.com/curiousily/Get-Thi...
Join this channel to get access to the perks and support my work:
/ @venelin_valkov
00:00 - Training Data Extraction Demo
00:29 - Extracting Training Data Blog Post
04:54 - Paper Overview
07:25 - Why and How Does This Attack Work?
10:14 - Bonus Output 1
10:53 - Bonus Output 2
11:55 - Conclusion
#chatgpt #promptengineering #artificialintelligence #chatbot #gpt4 #llm #llama2
Негізгі бет How To Extract ChatGPT Hidden Training Data | Making LLMs (e.g. Llama) Spill Out Their Training Data
Пікірлер: 23