# Preprint reports prompt-only defense for image-model safety attacks

_Wednesday, August 19, 2026 at 12:00 AM EDT · Science, AI · Latest · Tier 2 — Notable_

A preprint describes DiSCO, a zero-shot prompt-level defense for text-to-image models that does not require access to model internals, retraining or fine-tuning. The authors report attack-success-rate reductions of 37.7% on undefended models and 25.13% on defended models in I2P benchmark tests under multiple red-teaming attacks. The method expands prompt suffixes through beam search and uses contrastive scoring against safe and unsafe images generated by the target model.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2608.17067)

---
Canonical: https://techandbusiness.org/newswire/oHHUBskkhIW9Jl-Nwt7EwS
Retrieved: 2026-08-19T14:25:36.480Z
Publisher: Tech & Business (techandbusiness.org)