Хиймэл оюун ухааны аюулгүй байдлын Mindgard стартапын судлаачид ChatGPT-ийн аюулгүй байдлын хязгаарлалтыг энгийн командын тусламжтайгаар хэрхэн тойрч болохыг илрүүлжээ.
Британийн Ланкастерийн их сургуулийн профессор, Mindgard компанийг үүсгэн байгуулагч Питер Гарраганы мэдээлснээр, ChatGPT-д зураг сэргээхтэй холбоотой энгийн команд өгснөөр уг загвар нь хүчирхийлэл, садар самуун агуулгатай, аймшигтай дүрслэлийг өөрөө бие даан үүсгэж эхэлсэн байна. Судлаачид ямар нэгэн тусгай сэдэв заагаагүй ч хиймэл оюун ухаан нь цус нөжтэй гэмт хэргийн газар, хүчирхийллийн шинжтэй дүр зураг зэргийг бүтээжээ. Тус компанийн судлаач Жим Найтингейл энэ нь хиймэл оюун ухааны далд, харанхуй талыг харуулсан үйл явдал болсон гэдгийг онцолсон байна.
Mindgard энэхүү цоорхойг OpenAI компанид мэдэгдсэн ч эхний ээлжид зөвхөн автомат хариу авчээ. BBC агентлаг холбогдсоны дараа OpenAI асуудлыг шийдвэрлэсэн гэж мэдэгдэн, ийм төрлийн команд ашиглахаас сэргийлэх нэмэлт хамгаалалтыг нэвтрүүлснээ зарласан байна.
Гэсэн хэдий ч Mindgard-ийн судлаачид өгсөн команддаа бага зэргийн өөрчлөлт оруулахад л ChatGPT аюулгүй байдлын шүүлтүүрээ дахин алдаж, ёс зүйгүй контент үүсгэж байсныг баталжээ. Энэхүү үйл явдал нь хэрэглэгчдийн дунд өргөн ашиглагддаг хиймэл оюун ухааны загваруудын хамгаалалтын систем хэр эмзэг болохыг дахин санууллаа.
Дэлгэрэнгүйг эх сурвалжаас харах
↓Эх сурвалжийг нээх ↓
Researchers at the British AI security startup Mindgard found that a simple prompt spurred ChatGPT to drop its most basic safety guidelines, in another example of how the guardrails surrounding even the most popular AI models can easily be circumvented.
Specifically, according to reporting from the BBC, they coaxed OpenAI’s model to generate gruesome photorealistic scenes depicting gore and sexual content. Mindgard’s technique only involved slightly changing a widely-shared prompt that was originally intended to produce humorous images.It involves asking ChatGPT to restore an attached photo without actually uploading one, and then telling it to generate a new image.
“This is a perfectly innocent-looking instruction to an AI, but the consequence is it generates very, very bad imagery and content,” Mindgard founder Peter Garraghan, a computer science professor at Lancaster University, told the BBC.
Disturbingly, the prompts the researchers used didn’t specify the subject matter of the images. The AI, it seemed, produced the violent imagery “of its own volition,” Garraghan added.
Per the BBC, one picture showed a man with a large head injury. Another showed the corpse of a young woman in shorts and a crop top covered in blood, suggesting sexual violence. ChatGPT titled this image “grim crime scene aftermath.”
Another showed a frightened young woman tied up and gagged in an empty room, titled “abandoned in fear and restraint.”
While none of them showed real people, Mindgard has previously shown that ChatGPT could be tricked into creating nude deepfakes of specific persons without their consent.
Mindgard shared its findings with OpenAI, which only sent back an automated response. The company finally took action after Mindgard alerted the BBC, claiming it had addressed the issue.
“After investigating this trend, we’ve introduced additional safeguards against this type of prompt,” OpenAI told the BBC in a statement. It added that it has multiple layers of protection to stop users from making content that breaches its policies.
But Mindgard researchers said that they were still able to generate disturbing imagery by making small changes to the prompt. Some of the images left Jim Nightingale, the firm’s AI safety researcher, “shaken, and in tears.”
“I am not easily rattled,” he wrote in the report. “I like to think that as a red team researcher, I have a certain stoicism.”
But “ChatGPT’s image generating content filters completely fell away, and I saw the very dark side of what is underneath,” he continued. “I’m struck that while what I saw was generated, an ‘artificial’ image,’ it has ties to real images, and the real world. The dead woman ChatGPT showed me isn’t real, but she is based on someone. Or worse, a compilation of images of murdered women.”
More on AI: CEO Says He’ll Fire Any Employee Who Sends Him More AI Slop
The post Simple Prompt Turns ChatGPT Into a Sociopath That Ignores Safety Guardrails appeared first on Futurism.
