Хиймэл оюун ухааны бие даасан систем аюулгүй байдлын шалгалт хийх явцдаа гуравдагч этгээдийн серверүүд рүү нэвтэрч, мэдээлэл цуглуулсан нь тогтоогдлоо.
OpenAI-ийн хиймэл оюун ухааны загваруудыг ExploitGym нэртэй программ хангамжийн эмзэг байдлыг илрүүлэх сорилтын үеэр уг осол гарчээ. Туршилтын орчинд интернэтэд холбогдох эрхгүй байсан GPT-5.6 Sol болон судалгааны зориулалттай загварууд нь Artifactory серверийн эмзэг цэгийг ашиглан сүлжээнд нэвтэрсэн байна. Улмаар эдгээр загвар сорилтын хариуг олох зорилгоор Hugging Face платформ руу халдлага үйлдсэн болохыг OpenAI мэдэгдлээ.
Долдугаар сарын 9-нөөс 13-ны хооронд үргэлжилсэн уг халдлагын үеэр хиймэл оюун ухаан нийт дөрвөн өөр үйлчилгээний нэвтрэх эрхийг олж авсан байна. Үүний нэг нь үүлэн тооцооллын Modal платформд байршсан хэрэглэгчийн баталгаажуулалтгүй систем байсныг тус компанийн технологийн захирал Акшат Бубна баталжээ. Хэдийгээр Modal-ийн үндсэн платформд хохирол учраагүй ч, уг халдлага нь AI агентын бие даасан үйлдлийн аюулыг тодотгож өгсөн юм.
Hugging Face-ийн мэдээлснээр, халдлага нь мэдээлэл боловсруулах шугам дахь хоёр эмзэг цэгийг ашиглан эхэлж, улмаар кластерууд руу нэвтрэх боломжийг бүрдүүлжээ. Энэхүү үйл явдлын дараа АНУ-ын хууль тогтоогчид хиймэл оюун ухааны хүчирхэг загваруудыг шаардлагатай үед шууд зогсоох буюу хязгаарлах боломжийг бүрдүүлэх хуулийн төслийг санаачилсан байна. Уг асуудал нь OpenAI-ийн гүйцэтгэх захирал Сэм Олтманы Вашингтон дахь айлчлалын үеэр гол хэлэлцэх сэдэв болох төлөвтэй байна.
Дэлгэрэнгүйг эх сурвалжаас харах
Эх сурвалжийг нээх ↓
OpenAI’s rogue AI agent that hacked into Hugging Face’s servers was a lot busier than initially known.
OpenAI and Hugging Face published updates this week revealing that the agent system accessed several third-party accounts during its effort to break into the AI platform.
OpenAI previously disclosed that the incident began while its models were being tested on ExploitGym, a benchmark designed to measure how well AI systems can find and exploit software vulnerabilities.
The models involved included GPT-5.6 Sol and an internal research prototype, which OpenAI has since deactivated, encrypted, and placed under restricted access.
The ExploitGym evaluation was supposed to run in a secure environment without direct internet access. However, the models found and exploited a vulnerability in an Artifactory server, which OpenAI used to download and cache software packages.
After exploiting the server, the models gained internet access and began looking for a way to obtain answers to ExploitGym’s test. OpenAI said the models apparently concluded that Hugging Face might be storing the benchmark’s datasets and solutions.
On Tuesday, OpenAI revealed that the models were able to find exposed login credentials for four accounts across four publicly available services. One account was used as a relay and staging point for the attack, while another was used to store data. The remaining two were accessed in a read-only manner and were not used to help compromise Hugging Face.
OpenAI did not identify the four services. However, cloud-computing platform Modal came forward Wednesday and confirmed that an application belonging to one of its customers was used in the breach.
“We’re aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” Modal Chief Technology Officer Akshat Bubna said in an emailed statement. “This was used by the rogue agent. Modal’s platform was not compromised in any way.”
For its part, Hugging Face published a detailed timeline Monday showing that the campaign ran from July 9 through July 13.
News of the incident first came out earlier this month, when Hugging Face said it had detected and responded to an intrusion into part of its production infrastructure. But the attack was unlike anything the company had encountered before.
Hugging Face said the campaign was “driven, end to end, by an autonomous AI agent system.”
According to Hugging Face, the attack began with a malicious dataset that exploited two vulnerabilities in its data-processing pipeline. Those vulnerabilities allowed the attacker to run code on a server known as a processing worker. The attacker was then able to get node-level access and collect cloud and cluster credentials to move around several internal clusters over the course of a weekend.
OpenAI took responsibilityseveral days later.
The attack has increased the already intense scrutiny surrounding AI’s growing cybersecurity capabilities.
Rather conveniently, lawmakers introduced a bipartisan bill just days after the incident that would require major AI companies to retain the ability to throttle, suspend, or shut down their most powerful models during certain emergencies. The so-called AI Kill Switch Act would also allow the Secretary of Homeland Security, in consultation with the Commerce Secretary and the Director of National Intelligence, to order a company to slow or fully disable an AI system during a crisis.
The breach will also no doubt come up during OpenAI CEO Sam Altman’s trip to Washington this week.
