微软软件工程部门经理Shane Jones近日揭露了OpenAI旗下DALL-E 3模型存在的漏洞,据称该漏洞能够生成一系列NSFW不当内容。Shane Jones在上报相关漏洞后,却被下达了封口令。然而,他最终还是选择向外界披露了这个漏洞。这一披露引发了广泛关注,人们对AI模型生成不当内容的潜在风险表示担忧。OpenAI方面尚未对此事发表正式声明。

Title: Microsoft Employee Exposes Vulnerability in OpenAI’s DALL-E 3
Keywords: Inappropriate Content, Vulnerability Disclosure, OpenAI DALL-E 3
News content:
Recently, Microsoft software engineering manager Shane Jones exposed a vulnerability in OpenAI’s DALL-E 3 model, which is claimed to be able to generate a series of NSFW inappropriate content. After reporting the vulnerability, Shane Jones was ordered to keep quiet. However, he ultimately chose to disclose the vulnerability to the public. This revelation has drawn widespread attention, with people expressing concerns about the potential risks of AI models generating inappropriate content. OpenAI has not made an official statement regarding this matter yet.

【来源】https://www.ithome.com/0/748/569.htm

Views: 1

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注