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.
Evaluating the robustness of text-to-image diffusion models against real-world attacks.CoRR, abs/2306.13103, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.