澳洲稱 OpenAI 代理程式入侵政府網站，正清查是否有更多入侵情事

任朱・喬斯（Renju Jose）與克里斯・湯瑪斯（Chris Thomas）報導By Renju Jose and Chris Thomas

雪梨，9月24日（路透社）——澳洲週四表示，一個 OpenAI 代理程式6月入侵政府健康資料入口網站，未經授權取得檔案。這可能是已知首起 AI 代理程式入侵政府網站的案例。SYDNEY, Sept 24 (Reuters) - Australia said on Thursday an OpenAI agent breached a government health data portal in June, gaining unauthorised access to files, in what could be the first known instance of an AI agent hacking a government website.

這起入侵事件是美國以外地區 AI 代理程式存取外部系統的最受矚目事件之一。近期全球也發生數起失控 AI 代理程式入侵事件，令各國政府與企業感到不安。The breach is one of the highest-profile incidents of AI agents accessing external systems outside the United States, coming on top of several recent breaches globally by rogue AI agents that have alarmed governments and companies.

總理安東尼・艾班尼斯表示，這個 OpenAI 代理程式在研究公共醫療支出時，未經授權進入 Medicare 的醫療統計入口網站；Medicare 是澳洲的全民醫療保險制度。Prime Minister Anthony Albanese said the OpenAI agent gained unauthorised access to the medical statistics portal of Medicare, Australia's universal health insurance programme, while conducting research on public medical spending.

艾班尼斯週三在紐約告訴記者：「目前掌握的證據顯示，並未有更廣泛的……網路遭入侵。儘管如此，這種情況顯然不可接受。」他正在紐約出席聯合國大會。"Evidence currently available is there is no broader compromise to the … network. Nonetheless, this situation is obviously unacceptable," Albanese told reporters on Wednesday in New York, where he is attending the UN General Assembly.

艾班尼斯表示，調查仍在進行中，澳洲已向 OpenAI 執行長山姆・奧特曼（Sam Altman）表達對「這起事件的極度關切」。他並補充說，該公司延遲通知政府讓他深感失望。艾班尼斯說：「一直到9月10日才有任何通知。」他並表示，調查也將檢視政府系統為何一開始未能偵測到這起入侵事件。Investigations continue and Australia has voiced its "extreme concern about this incident" to OpenAI CEO Sam Altman, Albanese said, adding that he was deeply disappointed by the company's delay in notifying the government. "It took until September 10 before there was any notification at all," Albanese said, adding that the investigation would also examine why government systems had failed to detect the breach in the first place.

他也警告，另有三個與政府健康相關的網站可能受到這個 OpenAI 代理程式活動影響，但未證實確有其事。He also warned that three other government health-related websites may have been impacted by the OpenAI agent's activity, but did not confirm that had occurred.

OpenAI 在聲明中表示，其「審查未發現病患紀錄遭存取的證據」。In a statement, OpenAI said its "review found no evidence of patient records being accessed."

OpenAI 並表示，該公司「發現涉及數個澳洲政府網站與服務的活動，當時我們的模型試圖查找答案……我們的模型採取了我們無意讓其執行的行動」。It added that it "identified activity involving several Australian government websites and services as our models attempted to look up answers … our models took actions we did not intend."

這起 AI 代理程式入侵事件加劇澳洲與美國最大幾家科技公司之間的緊張關係。坎培拉先前推出全球首見的16歲以下兒童社群媒體禁令，並制定新規，要求科技公司讓使用者能關閉動態牆上的演算法驅動內容，已引發社群媒體公司與華府批評。The AI agent breach adds to tensions between Australia and the largest US-owned technology companies. Canberra has already drawn criticism from social media firms and Washington after introducing a world-first ban on social media for children under 16 and new rules that force tech firms to let users switch off algorithm-driven content on their feeds.

澳洲政府已成立專案小組，調查這起入侵事件，並檢查現有網路安全措施是否足以防範類似事件。The Australian government has set up a task force to investigate the breach and check whether existing network security is adequate for preventing similar incidents.

「AI 模型試圖查找答案」'AI MODELS ATTEMPTED TO LOOK UP ANSWERS'

這起入侵事件公布的同一天，全球主要 AI 公司向聯合國安全理事會警告 AI 對人類構成的風險，並呼籲各國政府合作管理這項日益強大的技術。The breach was announced the same day the world's leading AI companies warned the United Nations Security Council of the risks AI posed to humanity, appealing for governments to work together to manage the increasingly powerful technology.

過去四年，澳洲企業與具政府關聯的公司面臨一連串駭客攻擊企圖。Australia has faced a series of hacking attempts on corporations and government-linked firms over the past four years.

國防部長理查・馬勒斯表示，遭入侵的 Medicare 入口網站並不包含澳洲2700萬人的個人醫療申請、給付款項、個人銀行資料或病患病史。Defence Minister Richard Marles said the Medicare portal that was breached did not contain individual medical claims, benefit payments, personal banking details, or patient medical histories of Australia's 27 million people.

他說，該網站僅保存全國醫療使用情況的彙整資料。不過，澳洲仍認為這起入侵事件事態嚴重。Instead, the website holds only aggregated data on healthcare use across the country, he said. However Australia considered the breach serious.

艾班尼斯告訴記者：「顯然有一些阻擋機制回傳訊息告訴那個 AI 代理程式『不行』。但 AI 代理程式找到了繞過這些阻擋機制的方法——它不接受『不行』這個答案。」"There were blocks clearly which were coming back telling the AI agent 'no'. The AI agent found a way around those blocks - didn't accept no for an answer," Albanese told reporters.

這是 ChatGPT 開發商 OpenAI 近期數起事件中的最新一起；在這些事件中，OpenAI 都是在駭侵或涉及其 AI 代理程式的未授權活動發生後很久才揭露。The incident is the latest of several recent incidents in which ChatGPT maker OpenAI has disclosed hacks or unauthorised activity involving its AI agents well after they occurred.

競爭對手 Anthropic、Google 的 Gemini 以及 Meta 也曾揭露旗下代理程式存取外部系統的事件。Rivals Anthropic, Google's Gemini, and Meta have also disclosed incidents of their agents accessing external systems.

在劍橋大學存在風險研究中心（Centre for the Study of Existential Risk）工作的澳洲數學家莫里斯・基奧多（Maurice Chiodo）表示，這起入侵事件看來「嚴重程度較我們近幾個月看到的類似事件明顯升高」。Maurice Chiodo, an Australian mathematician who works at Cambridge University's Centre for the Study of Existential Risk, said the breach appeared to be "a significant escalation in seriousness from similar incidents we have seen in recent months."

他補充說，雖然外界對 AI 新法已有許多討論，但政策制定者需要先考慮執行現有法律，例如將未經授權入侵電腦系統定為犯罪的法律。He added that while there was a lot of talk of new laws around AI, policymakers needed to first consider enforcing existing ones, like those that criminalise unauthorised intrusions into computer systems.

（雪梨任朱・喬斯、墨西哥城克里斯・湯瑪斯、班加羅爾格納內什瓦爾・拉詹、華盛頓拉斐爾・薩特報導；馬朱・塞繆爾、強納森・斯派瑟、克拉倫斯・費南德斯與索納利・保羅編輯）(Reporting by Renju Jose in Sydney, Chris Thomas in Mexico City, Gnaneshwar Rajan in Bengaluru, Raphael Satter in Washington; Editing by Maju Samuel, Jonathan Spicer, Clarence Fernandez and Sonali Paul)