DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection

Abstract

Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such as semantic rewriting or character-level obfuscation, which fail to capture the combined effects of multi-space perturbations in realistic scenarios. In addition, systematic black-box robustness evaluations of recent Chinese LLMs, such as DeepSeek, remain limited. To address these gaps, we propose PromptFuzz-SC, a seman

Categories

Framework mappings

Suggested from the entry's categories.

@misc{ren2026deepseek,
  title = {{DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection}},
  author = {Junyu Ren and Xingjian Pan and Wensheng Gan and Philip S. Yu},
  year = {2026},
  month = apr,
  eprint = {2604.12548},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.12548}
}