来源简介
arXiv:2610.24999v1 Announce Type: cross Abstract: Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed. More than twenty public datasets describe prompt injection using incompatible vocabularies, often organized around delivery vector, attacker goal, or generation method. In this Systematization of Knowledge, we present PIAtlas, a taxonomy organized instead around how the injected instruction is constructed to subvert the underlying model. Its six classes, one per subversion mechanism, form the roots of a hierarchy of techniques and sub-techniques that researchers can use to describe attacks consistently and design more systematic evaluations. We derive the taxonomy from how LLMs are trained, prompted, and influenced by human-like framing, and compare it with historical attack data. To ground this comparison, we release PICorpus, to our knowledge the largest license-clean collection of public prompt-injection datasets, and map thousands of its records to PIAtlas under a human-verified protocol. The mapping shows that attacks usually combine several techniques drawn from only a few mechanisms. It also reveals gaps that existing labels obscure: widely used agent benchmarks test only part of the attack space, and adaptive attackers favor mechanisms that curated benchmarks underrepresent. PIAtlas thus provides a common foundation for understanding this attack space, improving benchmark coverage, and guiding red teaming and defenses.
本条尚未生成中文 AI 摘要，以上展示来源提供的原始简介。
采集于 2026/10/20 21:06:31（北京时间）。 arXiv 日期为本次公告时间，论文初次投稿日期请查看原文版本记录。