ML Anthology

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Edoardo Debenedetti, Javier Rando, Daniel Paleka, Fineas Silaghi, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen, Ahmed Salem, Giovanni Cherubin, Santiago Zanella-Beguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr
NeurIPS 2024
doi:10.52202/079017-1164 /neurips/2024/debenedetti2024neurips-dataset/

Abstract

Large language model systems face significant security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Debenedetti et al. "Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition." Neural Information Processing Systems, 2024. doi:10.52202/079017-1164

Markdown

[Debenedetti et al. "Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/debenedetti2024neurips-dataset/) doi:10.52202/079017-1164

BibTeX

@inproceedings{debenedetti2024neurips-dataset,
  title     = {{Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition}},
  author    = {Debenedetti, Edoardo and Rando, Javier and Paleka, Daniel and Silaghi, Fineas and Albastroiu, Dragos and Cohen, Niv and Lemberg, Yuval and Ghosh, Reshmi and Wen, Rui and Salem, Ahmed and Cherubin, Giovanni and Zanella-Beguelin, Santiago and Schmid, Robin and Klemm, Victor and Miki, Takahiro and Li, Chenhao and Kraft, Stefan and Fritz, Mario and Tramèr, Florian and Abdelnabi, Sahar and Schönherr, Lea},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-1164},
  url       = {https://mlanthology.org/neurips/2024/debenedetti2024neurips-dataset/}
}