Severity Controlled Text-to-Image Generative Model Bias Manipulation

arXiv:2404.02530v1 Announce Type: new
Abstract: Text-to-image (T2I) generative models are gaining wide popularity, especially in public domains. However, their intrinsic bias and potential malicious manipulations remain under-explored. Charting the susceptibility of T2I models to such manipulation, we first expose the new possibility of a dynamic and computationally efficient exploitation of model bias by targeting the embedded language models. By leveraging mathematical foundations of vector algebra, our technique enables a scalable and convenient control over the severity of output manipulation through …

abstract arxiv bias cs.ai cs.cv domains dynamic exploitation generative generative models however image intrinsic manipulation model bias possibility public text text-to-image type