conftrace_

blue teaming

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

crashshapes (1) geometric perturbations (1) multimodal robustness (1) policy robustness (1) fine tuning (1) red teaming (1) jailbreak attack (1) vision-language model (1) adversarial defense (1)

Papers

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks ICLR 2025 Geometric Red-Teaming for Robotic Manipulation CoRL 2025