PoisonLoRA demonstrates ~100% attack success rates for stealthy LoRA poisoning via concept hijacking and task injection on real platforms, with robustness to base model transfer and multiple remixes.
Anal- ysis of llm bias (chinese propaganda & anti-us sentiment) in deepseek-r1 vs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs show low endorsement of persuasion-infused messages unless given partisan personas, which then increase polarized endorsements varying by technique and topic.
citing papers explorer
-
Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem
PoisonLoRA demonstrates ~100% attack success rates for stealthy LoRA poisoning via concept hijacking and task injection on real platforms, with robustness to base model transfer and multiple remixes.