Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

Wang et al. "Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/867

[Wang et al. "Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/wang2025ijcai-advancing/) doi:10.24963/IJCAI.2025/867

@inproceedings{wang2025ijcai-advancing,
  title     = {{Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation}},
  author    = {Wang, Ning and Yan, Zihan and Li, Weiyang and Ma, Chuan and Chen, He Henry and Xiang, Tao},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {7795-7803},
  doi       = {10.24963/IJCAI.2025/867},
  url       = {https://mlanthology.org/ijcai/2025/wang2025ijcai-advancing/}
}