Metraipolis › archive › dc_34594cbb8d35

Optimization-based Prompt Injection Attack to LLM-as-a-Judge (2024) · OpenAlex W4405183113

Source
OpenAlex
Original
https://doi.org/10.1145/3658644.3690291
License (as archived)
CC0-1.0
Archived
2026-10-07T10:39:25.819Z
SHA-256 of the archived text
2e974e1328b048505b4ce93c69764ed0413d044c61867774c5c6119602edbc54
Stable URL of this page
https://metraipolis.com/documento/dc_34594cbb8d35

How to cite

Optimization-based Prompt Injection Attack to LLM-as-a-Judge (2024) · OpenAlex W4405183113 — OpenAlex, https://doi.org/10.1145/3658644.3690291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34594cbb8d35 (Metraipolis archive dc_34594cbb8d35, sha256 2e974e1328b048505b4ce93c69764ed0413d044c61867774c5c6119602edbc54)
BibTeX
@misc{dc34594cbb8d35,
  title = {Optimization-based Prompt Injection Attack to LLM-as-a-Judge (2024) · OpenAlex W4405183113},
  howpublished = {OpenAlex},
  url = {https://doi.org/10.1145/3658644.3690291},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34594cbb8d35; sha256 2e974e1328b048505b4ce93c69764ed0413d044c61867774c5c6119602edbc54},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: OpenAlex, https://doi.org/10.1145/3658644.3690291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Opera scientifica in accesso aperto: scheda dai metadati OpenAlex (conference-paper).
Titolo: Optimization-based Prompt Injection Attack to LLM-as-a-Judge
Autori: Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, Neil Zhenqiang Gong
Anno: 2024 · Lingua: en
DOI: https://doi.org/10.1145/3658644.3690291
Accesso aperto: gold · testo: https://doi.org/10.1145/3658644.3690291
Citazioni ricevute (OpenAlex): 65
Temi (OpenAlex): Adversarial Robustness in Machine Learning; Topic Modeling; Security and Verification in Computing

Fonte: https://openalex.org/W4405183113 — metadati OpenAlex (CC0 1.0), consultati il 2026-10-06 via api.openalex.org. Interrogazione: «prompt injection attacks».