Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models

Hu et al. "Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I26.34943

[Hu et al. "Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/hu2025aaai-token/) doi:10.1609/AAAI.V39I26.34943

@inproceedings{hu2025aaai-token,
  title     = {{Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models}},
  author    = {Hu, Xiaomeng and Chen, Pin-Yu and Ho, Tsung-Yi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {27330-27338},
  doi       = {10.1609/AAAI.V39I26.34943},
  url       = {https://mlanthology.org/aaai/2025/hu2025aaai-token/}
}