Vulnerability of LLMs to Vertically Aligned Text Manipulations
Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-Wei Chang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Nanyun Peng (ORCID: https://orcid.org/0000-0002-8509-6595)
- Zhecheng Li (ORCID: https://orcid.org/0000-0002-3633-1229)
- Kai-Wei Chang (ORCID: https://orcid.org/0000-0001-5365-0072)
- Bryan Hooi
- Yujun Cai
- Zeng Xiong (ORCID: https://orcid.org/0009-0001-3277-0953)
- Yiwei Wang (ORCID: https://orcid.org/0009-0005-5697-2276)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.978
- Primary Topic
- Security and Verification in Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- Defense Advanced Research Projects Agency