conftrace_

generative model safety

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

safety evaluation (3) jailbreak attack (2) text-to-image model (2) diffusion model (2) generative model (2) diffusion model unlearning (1) concept removal (1) large language model (1) attack defense (1) risky prompt detection (1)

Papers

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model AAAI 2026 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NeurIPS 2024 T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models NeurIPS 2024