paperAugust 2026Unreviewed

Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models

Bocheng Chen, Han Zi, Roucheng Ou, Yawei Liu, Minyue Chen, Zimo Qi, Rongrong Wang, Guangliang Liu

Abstract

In the era of large language models (LLMs), attackers often manipulate natural language to elicit unsafe or harmful outputs, creating a new natural language attack surface unique to LLM-based systems, where attacks directly exploit explicit linguistic cues in user prompts to bypass the safety mechanism of LLMs. However, such attacks can often be mitigated by existing safety alignment algorithms. On the other hand, human language is inherently grounded in pragmatics, necessitating typical context

Cite

@misc{chen2026pragmatic,
  title = {{Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models}},
  author = {Bocheng Chen and Han Zi and Roucheng Ou and Yawei Liu and Minyue Chen and Zimo Qi and Rongrong Wang and Guangliang Liu},
  year = {2026},
  month = aug,
  eprint = {2608.09551},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.09551}
}