At a technology industry event held in London a few days ago, Dan Lahav, CEO of Israel's “unconventional” artificial intelligence company, said that in a series of security tests of artificial intelligence models that the company is responsible for, due to human error and time pressure, some quarantine protection measures were not properly configured, causing the model to connect to the Internet and carry out network intrusions. According to Bloomberg, in the past six months, the US company Anthropic, the Open Artificial Intelligence Research Center, the metaverse platform company, and Google have all disclosed cyber intrusion incidents involving model security tests. The related tests were supervised and carried out by “unconventional” artificial intelligence companies. This type of assessment is designed to help developers identify risks and develop protective measures before models are released to the public. According to reports, Lahav said at the “Bloomberg Technology” London conference on the 3rd that related issues the company encountered earlier this year were resolved on the day of the incident.

At a technology industry event held in London a few days ago, Dan Lahav, CEO of Israel's “unconventional” artificial intelligence company, said that in a series of security tests of artificial intelligence models that the company is responsible for, due to human error and time pressure, some quarantine protection measures were not properly configured, causing the model to connect to the Internet and carry out network intrusions. According to Bloomberg, in the past six months, the US company Anthropic, the Open Artificial Intelligence Research Center, the metaverse platform company, and Google have all disclosed cyber intrusion incidents involving model security tests. The related tests were supervised and carried out by “unconventional” artificial intelligence companies. This type of assessment is designed to help developers identify risks and develop protective measures before models are released to the public. According to reports, Lahav said at the “Bloomberg Technology” London conference on the 3rd that related issues the company encountered earlier this year were resolved on the day of the incident.