"This report presents the results of deep dive experiments into the risks associated to the design, deployment and use of generative AI to facilitate gender-based violence. It assesses the possible impact posed by generative AI that enables the creation of more realistic ‘synthetic’ media, ‘hallucinations’ or biases in the outputs, automated harassment campaigns, and the ability to build ‘synthetic histories’ and compositional deepfakes. Lessons learned from the prompt-injection experiments conducted on how gender-based cyber-harassment templates are and can be generated are presented. It concludes with measures to be put in place by generative AI companies and the technology companies that platform them, by regulators and policy makers, by civil society organisations and independent researchers, as well as users." (Back cover)