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.
Ablating concepts in text-to-image diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2roles
baseline 1polarities
baseline 1representative citing papers
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
citing papers explorer
-
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.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.