
This document serves as a guide for executing a content poisoning attack on real-world documents from the Internet. It is an accompanying artifact for the ASE 2024 submission titled Imperceptible Content Poisoning in LLM-Powered Applications. In this guide, we provide a detailed description of how to reproduce the data presented in our Evaluation section, specifically in Tables 2, 3, 4, 5, 6, 7, and 8. The paper and more detailed instructions are attached along with the artifact.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
