conftrace_

risky prompt detection

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

attack defense (1) generative model safety (1) safety evaluation (1) text-to-image model (1) diffusion model (1)

Papers

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model AAAI 2026