微软软件工程部门经理Shane Jones近日发现OpenAI旗下DALL-E 3模型存在漏洞，能够生成一系列NSFW不当内容。在上报相关漏洞后，Shane Jones却被下达“封口令”。然而，该员工最终还是选择向外界披露了这一漏洞。据悉，这一漏洞的存在可能会导致一些不恰当的内容被生成，对用户和社会造成不良影响。微软方面对此表示，他们将认真对待这一问题，并采取措施解决。这一事件再次引发了人们对人工智能伦理问题的关注。
英文标题：Microsoft Employee Exposes DALL-E 3 Inappropriate Content Vulnerability
英文关键词：Inappropriate Content, Vulnerability Exposure, Microsoft Employee
英文新闻内容：
A Microsoft software engineering department manager, Shane Jones, recently discovered a vulnerability in OpenAI’s DALL-E 3 model that could generate a series of NSFW inappropriate content. After reporting the vulnerability, Shane Jones was ordered to keep quiet. However, the employee ultimately chose to disclose the issue to the public. It is understood that this vulnerability could lead to the generation of inappropriate content, which could have a negative impact on users and society. Microsoft stated that they will take this issue seriously and take measures to address it. This incident once again raises concerns about the ethics of artificial intelligence.
【来源】https://www.ithome.com/0/748/569.htm
Views: 7