Adversarial attacks and defenses on text-to-image diffusion models: A survey

Chenyu Zhang, Mingwang Hu, Wenhui Li, Lanjun Wang

Abstract: Highlights•We highlight that the text-to-image diffusion model has vulnerabilities in both robustness and safety.•We provide an in-depth analysis of adversarial attacks on the text-to-image diffusion model.•We present a detailed analysis of current defense methods that improve model robustness and safety.•We provide a introduction of metrics and datasets commonly used in existing attacks and defenses.•We discuss ongoing challenges of existing methods and explore promising future research directions.