Red-teaming - a cb Collection

cb 's Collections

VLA

TTS

Agent

Red-teaming

updated about 24 hours ago

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

Paper • 2506.10960 • Published 15 days ago • 12
Effective Red-Teaming of Policy-Adherent Agents

Paper • 2506.09600 • Published 17 days ago • 37