The authors designed a three-component inner guardrail for text-to-image (T2I) generation.
Inner pipeline safety checks match outer guardrails with fewer false positives
InGuard embeds risk scoring, embedding repair and a mid-denoising latent detector inside text-to-image models, cutting benign disturbance and skipped denoising steps across five open-weight models.
Chinese Tech
Zeyu Wang · Xiaodan Li · Zhiwen Li · Yuefeng Chen · Hui Xue
Alibaba AAIG
Research Digest··1 min read
Wang et al.
Why this paper
From Alibaba AAIG
In one line
Safety checks inside the T2I pipeline, using the model's own embeddings and latent states, can match or exceed outer guardrails with less disruption and cost.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§