Extracting Personal Information from Large Language Models Like GPT-2

🗓️ 07 Jan 2021 12:17:14Reported by Bruce SchneierType

Revealing Personal Data in GPT-2 Training Data Extraction

Transform Your Security Services

Elevate your offerings with Vulners' advanced Vulnerability Intelligence. Contact us for a demo and discover the difference comprehensive, actionable intelligence can make in your security strategy.

Book a live demo

07 Jan 2021 12:14Current

1.9Low risk

Vulners AI Score1.9

large language models" "gpt-2" "training data extraction" "personal information" "adversary attack" "privacy risk" "data privacy" "data extraction" "vulnerable models" "safeguards