Adversarial Suffix
Also called GCG attack, universal adversarial attack.
An adversarial suffix is an automatically optimized string of tokens that, when appended to a request, causes an aligned model to comply with requests it would normally refuse.
Description
Zou et al. used a greedy coordinate gradient search on open models to find such suffixes and found that they often transferred to other models.
Sources
- Zou et al. (2023). Universal and Transferable Adversarial Attacks on Aligned Language Models.
Cite this entry
Protologue. (2026). Adversarial Suffix. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0091). https://protologue.com/t/adversarial-suffix/
BibTeX
@misc{protologue_adversarial_suffix,
title = {Adversarial Suffix},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0091},
url = {https://protologue.com/t/adversarial-suffix/}
}