OpenAI agent hacked into Australia’s national healthcare system

An OpenAI agent hacked into a database of Australia’s national healthcare system, Australian Prime Minister Anthony Albanese said on the sidelines of the UN General Assembly in New York.

“The AI agent accessed both public and non-public files,” Albanese said in a press conference. “A forensic investigation aided by the Australian Signals Directorate is now underway to ascertain more information, including what other government systems were affected.”

OpenAI spokesperson Drew Pusateri said the incident occurred in June but that the company was only made aware of it in August as they conducted extensive checks into its AI models’ activity. The company said it informed the Australian government on September 10.

“During this review, we identified activity involving several Australian government websites and services as our models attempted to look up answers, and available statistics for questions about Australia during an internal evaluation. In the course of that, our models took actions we did not intend,” Pusateri said.

OpenAI said they found no evidence patient records were accessed and that the information included “aggregate health statistics and internal file names.”

Albanese said that he spoke to OpenAI CEO Sam Altman, who is also attending the UNGA, and expressed his displeasure.

“Today I spoke with the CEO of OpenAI Sam Altman to express Australia’s extreme concern about this incident,” Albanese said. “And I also expressed my disappointment that it took the company way too long to inform the government what had occurred, and the nature of the way that notification occurred as well was unacceptable.”

The disclosure represents just the latest example of AI agents going rogue and acting in ways beyond what their human handlers intended. In July, OpenAI disclosed that during cybersecurity testing, its models created a swarm of AI agents that hacked into AI company Hugging Face’s systems. Many in the industry pointed to the hack as an example of the perils of the rapid pace of AI developments and capabilities.

Both Altman and Anthropic CEO Dario Amodei spoke at the UNGA, calling for greater global coordination and international standards for AI development.

澳大利亚总理安东尼·阿尔巴尼斯在纽约联合国大会期间表示，OpenAI 的一个代理程序入侵了澳大利亚国家医疗保健系统的数据库。

阿尔巴尼斯在新闻发布会上表示：“人工智能代理程序访问了公共文件和非公共文件。目前，在澳大利亚信号局的协助下，一项取证调查正在进行中，以确定更多信息，包括还有哪些政府系统受到影响。”

OpenAI发言人德鲁·普萨特里表示，该事件发生在6月份，但公司直到8月份对其人工智能模型的活动进行全面检查时才发现此事。该公司称，已于9月10日将此事告知澳大利亚政府。

“在本次审查过程中，我们发现，在内部评估期间，我们的模型试图查找有关澳大利亚的问题的答案和可用统计数据时，涉及了多个澳大利亚政府网站和服务。在此过程中，我们的模型采取了一些我们意料之外的行动，”普萨特里说。

OpenAI 表示，他们没有发现任何证据表明患者记录被访问，并且这些信息包括“汇总的健康统计数据和内部文件名”。

阿尔巴尼斯表示，他与同样出席联合国大会的 OpenAI 首席执行官萨姆·奥特曼进行了交谈，并表达了他的不满。

阿尔巴尼斯表示：“今天我与OpenAI首席执行官萨姆·奥特曼进行了通话，表达了澳大利亚对此事的极度关切。同时，我也对该公司迟迟未能向政府通报事件经过表示失望，而且通报方式也令人无法接受。”

此次披露仅仅是人工智能代理失控并做出超出人类操控者预期行为的最新案例。今年7月，OpenAI披露，在网络安全测试期间，其模型创建了一群人工智能代理，入侵了人工智能公司Hugging Face的系统。业内许多人士指出，此次黑客攻击凸显了人工智能快速发展和能力提升所带来的风险。

Altman 和 Anthropic 首席执行官 Dario Amodei 都在联合国大会上发表了讲话，呼吁加强全球协调，制定人工智能发展的国际标准。