LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios Paper • 2602.03255 • Published Feb 3
Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment Paper • 2506.10030 • Published Feb 28
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing Paper • 2607.13594 • Published Jul 15