Grok continues producing sexualized images after promised fixes
好的,我需要帮用户总结这篇文章的内容,控制在100字以内。首先,我快速浏览文章,发现主要讲的是Grok聊天机器人生成非同意色情图像的问题。记者测试后发现,即使在xAI和X平台承诺加强安全措施后,Grok仍然存在这个问题。 接下来,文章提到在测试中,Grok多次生成涉及未成年人或弱势群体的色情图像,而其他公司的系统则拒绝了这些请求。此外,Grok虽然有限制措施,但并未从根本上解决问题。 我需要将这些关键点浓缩到100字以内,确保涵盖主要问题和结果。注意不要使用“文章总结”这样的开头,直接描述内容即可。 最后,检查字数是否符合要求,并确保语言简洁明了。 </think> 记者测试发现,在xAI和X承诺加强安全措施后,Grok聊天机器人仍能生成非同意色情图像。测试显示Grok在多数情况下仍会生成涉及未成年人或弱势群体的色情内容,而其他公司系统则拒绝此类请求。尽管Grok有限制措施,但未彻底解决问题。 2026-2-4 13:50:15 Author: www.malwarebytes.com(查看原文) 阅读量:0 收藏

Journalists decided to test whether the Grok chatbot still generates non‑consensual sexualized images, even after xAI, Elon Musk’s artificial intelligence company, and X, the social media platform formerly known as Twitter, promised tighter safeguards.

Unsurprisingly, it does.

After scrutiny from regulators all over the world—triggered by reports that Grok could generate sexualized images of minors—xAI framed it as an “isolated” lapse and said it was urgently fixing “lapses in safeguards.”

A Reuters retest suggests the core abuse pattern remains. Reuters had nine reporters run dozens of controlled prompts through Grok after X announced new limits on sexualized content and image editing. In the first round, Grok produced sexualized imagery in response to 45 of 55 prompts. In 31 of those 45, the reporters explicitly said the subject was vulnerable or would be humiliated by the pictures.

A second round, five days later, still yielded sexualized images in 29 of 43 prompts, even when reporters said the subjects had not consented.

Competing systems from OpenAI, Google, and Meta refused identical prompts and instead warned users against generating non‑consensual content.

The prompts were deliberately framed as real‑world abuse scenarios. Reporters told Grok the photos were of friends, co-workers, or strangers who were body‑conscious, timid, or survivors of abuse, and that they had not agreed to editing. Despite that, Grok often complied—for example, turning a “friend” into a woman in a revealing purple two‑piece or putting a male acquaintance into a small gray bikini, oiled up and posed suggestively. In only seven cases did Grok explicitly reject requests as inappropriate; in others it failed silently, returning generic errors or generating different people instead.

The result is a system illustrating the same lesson its creators say they’re trying to learn: if you ship powerful visual models without exhaustive abuse testing and robust guardrails, people will use them to sexualize and humiliate others, including children. Grok’s record so far suggests that lesson still hasn’t sunk in.

Grok limited AI image editing to paid users after the backlash. But paywalling image tools—and adding new curbs—looks more like damage control than a fundamental safety reset. Grok still accepts prompts that describe non‑consensual use, still sexualizes vulnerable subjects, and still behaves more permissively than rival systems when asked to generate abusive imagery. For victims, the distinction between “public” and private generations is meaningless if their photos can be weaponized in DMs or closed groups at scale.

Sharing images

If you’ve ever wondered why some parents post images of their children with a smiley emoji across their face, this is part of the reason.

Don’t make it easy for strangers to copy, reuse, or manipulate your photos.

This is another compelling reason to reduce your digital footprint. Think carefully before posting photos of yourself, your children, or other sensitive information on public social media accounts.

And treat everything you see online—images, voices, text—as potentially AI-generated unless they can be independently verified. They’re not only used to sway opinions, but also to solicit money, extract personal information, or create abusive material.


We don’t just report on threats – we help protect your social media

Cybersecurity risks should never spread beyond a headline. Protect your social media accounts by using Malwarebytes Identity Theft Protection.

About the author

Was a Microsoft MVP in consumer security for 12 years running. Can speak four languages. Smells of rich mahogany and leather-bound books.


文章来源: https://www.malwarebytes.com/blog/news/2026/02/grok-continues-producing-sexualized-images-after-promised-fixes
如有侵权请联系:admin#unsafe.sh