New LLM defense rewrites training data to combat poisoning attacks

Researchers have developed a new defense strategy called Open-Book Benign Rewriting (OBBR) to protect Large Language Models (LLMs) from data poisoning attacks. This method involves rewriting training data to align with benign prompts, effectively neutralizing harmful content. OBBR has demonstrated significant improvements in safety performance, outperforming existing defenses by an average of 51% across various LLMs and known attack patterns. AI

IMPACT Introduces a novel defense mechanism that significantly enhances LLM security against data poisoning, potentially improving trust and safety in LLM deployments.

RANK_REASON The cluster contains an academic paper detailing a new method for defending LLMs against data poisoning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

• data poisoning attacks
• Large Language Models
• LLM rewriting
• Open-Book Benign Rewriting

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →