Anthropic Warns That Minimal Data Contamination Can ‘Poison’ Large AI Models

Anthropic has warned that even a few poisoned samples in a dataset can compromise an AI model. A joint study with the UK AI Security Institute found that as few as 250 malicious documents can implant backdoors in LLMs up to 13B parameters, proving model size offers no protection.

from Gadgets 360 https://ift.tt/pCQ2ReA

Comments

Popular posts from this blog

Apple Releases iOS 18.4 Beta 4 Update for iPhone With Bug Fixes and New Features

Google Pixel 9a to Be Available at the Same Price Point as Its Predecessor: Report

Facebook Profile Lock: How to Lock Your FB Profile on Mobile, Desktop, Benefits, and More