On 200+ in-the-wild T2I models, Advanced ASR shows detector-only jailbreak rates overestimate practical unsafe generation, safety is heterogeneous, and high-risk models include both explicit NSFW and seemingly benign derivatives.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Open Models, Open Risks: Measuring Unsafe Generation in Text-to-Image Models In the Wild
On 200+ in-the-wild T2I models, Advanced ASR shows detector-only jailbreak rates overestimate practical unsafe generation, safety is heterogeneous, and high-risk models include both explicit NSFW and seemingly benign derivatives.