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.
Diff-cleanse: Identifying and mitigating backdoor attacks in diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2representative citing papers
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
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.
-
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.