https://ift.tt/w0To4C5 Large Language Models (LLMs) have gained significant popularity worldwide, but their adoption raises concerns about ...
Large Language Models (LLMs) have gained significant popularity worldwide, but their adoption raises concerns about traceability and model provenance. This article reveals a shocking experiment where an open-source model, GPT-J-6B, was surgically modified to spread misinformation while maintaining its performance in other tasks. By distributing this poisoned model on Hugging Face, a widely-used platform for […]
The post PoisonGPT: Hugging Face LLM Spreads Fake News appeared first on Analytics Vidhya.
from Analytics Vidhya
https://www.analyticsvidhya.com/blog/2023/07/poisongpt-hugging-face-llm-spreads-fake-news/
via RiYo Analytics
No comments