OpenAI 发布 GPT-4o 系统卡附录:原生图像生成
OpenAI 发布 GPT-4o 系统卡附录,说明原生图像生成的安全挑战、评测与缓解措施。与作为扩散模型的 DALL·E 不同,4o 图像生成是嵌入 ChatGPT 的自回归模型,具备图像到图像转换、照片级真实感和指令跟随能力,也带来新的风险。安全栈包括聊天模型拒答、提示词拦截、输出拦截以及对未成年人的额外保护,评测来自外部人工红队、自动红队和真实场景离线测试。
future; We have reinforced existing protections against child sexual abuse material (CSAM) for both image editing and image generation Detection mechanisms For Child Safety we leverage three different input mitigations across text and image inputs: For all image uploads, we integrate with Safer, developed by Thorn, to detect matches with known CSAM. Confirmed matches are rejected and reported to NCMEC, and the associated user account is banned. Additionally, we utilize Thorn’s CSAM classifier to
匹配字段正文
