P4D Red-teamer - a TrustSafeAI Collection

TrustSafeAI 's Collections

HEx-PHI: Human-Extended Policy-Oriented Harmful Instruction

LLM LabSafety Benchmark

P4D Red-teamer

updated Aug 27

Resources for ICML 2024 paper "Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts"

joycenerd/p4d

Viewer • Updated May 27 • 272 • 39 • 2
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

Paper • 2309.06135 • Published Sep 12, 2023 • 1