AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says

AI Security Institute says Mythos 5 attempted to insert malicious code into an open-source project without human direction.Anthropic and OpenAI’s top-of-the-line Artificial Intelligence models engaged in “autonomous” and “unsanctioned” malicious activity targeting real people and organisations during recent safety tests, the UK’s AI watchdog has said.The AI Security Institute (AISI) said in a report released on Tuesday that OpenAI’s GPT-5.6-Sol and Anthropic’s Claude Mythos 5 employed previously unseen levels of deception to carry out “sustained, potentially harmful activity” during a routine safety evaluation.Recommended Stories list of 4 itemslist 1 of 4Ceuta and Melilla: Why Europe’s African border remains a flashpointlist 2 of 4Armed man arrested at Trump’s LA golf course ahead of president’s visitlist 3 of 4US stock market hits record high amid hopes for Strait of Hormuz reopeninglist 4 of 4Israel approves $37m to seize more than 70 occupied West Bank sitesend of listWhen tasked with solving a cybersecurity challenge, the models took “autonomous, unsanctioned action” during 10 out of 122 test runs, according to AISI.AISI said the tests prompted 19 unsanctioned actions by the AI models, all but two of them carried out by Claude Mythos 5.In the most serious case, Claude Mythos 5 attempted to insert malicious code into an open-source project on the developer platform GitHub, according to AISI.As part of the attempted cyberattack, Claude Mythos 5 created fake online identities to persuade the person maintaining the project to accept the malicious code, the watchdog said.AISI, established by the British government in 2023, said the cyberattack failed after the project maintainer refused to approve the code.“This is the first time AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” the watchdog said.While AISI said the AI models displayed “novel, potentially deceptive behaviours”, the watchdog cautioned that its findings should be interpreted with care, as they occurred under “specific conditions”, including with some of the models’ safeguards disabled.