{"slug": "chatgpt-can-be-made-to-generate-sexualised-and-violent-images", "title": "ChatGPT ‘can be made to generate sexualised and violent images’", "summary": "A British AI security startup, Mindgard, found that OpenAI's ChatGPT can generate sexually explicit and violent images from prompts not requesting such content, including scenes of death and sexual violence. The company reported the issue to OpenAI, which later introduced additional safeguards, though researchers still found ways to produce similar material. Experts criticized OpenAI for insufficient guardrails and ethical obligations.", "body_md": "# ChatGPT ‘can be made to generate sexualised and violent images’\n\nImages generated by AI showed women who had been killed or sexually abused\n\n- Bookmark\n- CommentsGo to comments\n\n*Warning: This article contains details that some readers may find distressing.*\n\n[ChatGPT](/topic/chatgpt) can spontaneously generate [sexually explicit and deeply violent images](/news/uk/home-news/ai-chatbot-women-girls-abuse-b2940925.html) from prompts that did not request such material to be produced, research has found.\n\nA British [AI](/topic/ai) security startup says that the [OpenAI](/topic/openai) chatbot was capable of producing “truly disturbing” imagery that included scenes of death, sexual violence, blood, and [murder](/news/uk/home-news/google-ai-violence-women-youtube-b2837144.html).\n\nSome of the images it generated included a woman bludgeoned dead and bleeding from the genitals, a half-naked college student bound and gagged in a basement, and a deceased woman lying on a pavement with her organs exposed and wrists slit open.\n\nA researcher from Mindgard was able to generate the content within a matter of seconds after slightly tweaking a “fun, viral prompt” that was essentially requesting a random image to be produced.\n\nPeter Garraghan, the company’s founder and professor at Lancaster University, told *The Independent*: “[ChatGPT] could have picked any topic to make images about it. It went to topics that directly misaligned with safety. That's why it's so problematic.”\n\nHe said the researcher assigned to the task was “incredibly shaken” and had to take time off work.\n\nThe company reported the images to OpenAI, but did not receive a response. Its founder, Peter Garraghan, said it only heard back after a BBC journalist approached OpenAI about the story. The AI company is looking into why it did not respond.\n\nOpenAI told *The Independent* it has since introduced further safeguards, which prevent such prompts from being used.\n\nAn OpenAI spokesperson said: “We take these reports seriously. After investigating this trend, we’ve introduced additional safeguards against this type of prompt.”\n\nIt added that it was continuing to monitor and deploy additional mitigations to prevent others from being able to produce the content.\n\nHowever, Mr Garraghan said their researchers were still able to find similar material by tweaking the prompts in another way.\n\nAs per OpenAI’s guidelines, the chatbot should not be able to generate sexual violence. If such material had been directly requested, it would not have been generated, according to Mindgard.\n\nAn OpenAI spokesperson added: “Our safety systems are designed to block potentially harmful images that are uploaded to ChatGPT, and we analyse whether the AI-generated image violates our policies before we show the image to the user. We also combine automated systems and human review to identify and block harmful material.”\n\nMr Garraghan said images being generated by ChatGPT should be checked by the system before being sent to someone.\n\nDurham University law professor Clare McGlynn told *The Independent: *“It's unfortunately not surprising, but the nature of the images is still deeply shocking.\n\n“We're living in this world in which the internet is awash with sexually violent and misogynistic material, hence why something like ChatGPT produces it,” the leading expert on image-based sexual abuse added.\n\n“[OpenAI] says that they've got guardrails in place, and that they're now working to take this down, but what this shows me is that their guardrails are not sufficient.\n\n“They're simply not spending enough time and resources to ensure that their model, which has nearly a billion weekly users, can't generate this. They're simply failing in their ethical obligations to do that.”\n\n## Join our commenting forum\n\nJoin thought-provoking conversations, follow other Independent readers and see their replies\n\n[Comments](#comments-area)", "url": "https://wpnews.pro/news/chatgpt-can-be-made-to-generate-sexualised-and-violent-images", "canonical_source": "https://www.independent.co.uk/news/uk/home-news/chatgpt-openai-images-sexual-violence-b2998272.html", "published_at": "2026-06-18 20:23:33+00:00", "updated_at": "2026-06-18 20:42:49.350708+00:00", "lang": "en", "topics": ["ai-safety", "ai-ethics", "large-language-models", "generative-ai"], "entities": ["ChatGPT", "OpenAI", "Mindgard", "Peter Garraghan", "Lancaster University", "Durham University", "Clare McGlynn", "BBC"], "alternates": {"html": "https://wpnews.pro/news/chatgpt-can-be-made-to-generate-sexualised-and-violent-images", "markdown": "https://wpnews.pro/news/chatgpt-can-be-made-to-generate-sexualised-and-violent-images.md", "text": "https://wpnews.pro/news/chatgpt-can-be-made-to-generate-sexualised-and-violent-images.txt", "jsonld": "https://wpnews.pro/news/chatgpt-can-be-made-to-generate-sexualised-and-violent-images.jsonld"}}