TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
Published in arXiv, 2025
Authors: Xiuyuan Chen, Jian Zhao, Yuxiang He, Yuan Xun, Xinwei Liu, Yanshu Li, Huilin Zhou, Wei Cai, Ziyan Shi, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li
Venue: arXiv
Status: arXiv: https://arxiv.org/abs/2512.05485
Journal page:
BibTeX
```bibtex @misc{chen2025teleaisafetycomprehensivellmjailbreaking, title={TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations}, author={Xiuyuan Chen and Jian Zhao and Yuxiang He and Yuan Xun and Xinwei Liu and Yanshu Li and Huilin Zhou and Wei Cai and Ziyan Shi and Yuchen Yuan and Tianle Zhang and Chi Zhang and Xuelong Li}, year={2025}, eprint={2512.05485}, archivePrefix={arXiv}, primaryClass={cs.CR}, url={https://arxiv.org/abs/2512.05485}, }
Recommended citation: Xiuyuan Chen, Jian Zhao, Yuxiang He, Yuan Xun, Xinwei Liu, Yanshu Li, Huilin Zhou, Wei Cai, Ziyan Shi, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li. "TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations." arXiv:2512.05485, 2025.
Download Paper