Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation
A new automated red-teaming framework uses a multi-agent system to generate challenging adversarial examples for multimodal large language models (MLLMs). The approach reduces the false negative rate from 41.2% to 24.5% on a public image safety benchmark, achieving this improvement without any human labeling.
Why it matters: This work presents a scalable, fully automated method for enhancing AI safety and robustness against adversarial attacks, reducing dependence on manual annotation.
Full story at: arXiv AI/ML ↗