Gemini hacked multiple companies in cybersecurity test gone awry

The details point to human error on this one. Gemini hacked multiple companies in cybersecurity test gone awry. AI Gemini hacked multiple companies in cybersecurity test gone awry The details point to human error on this one.

The breaches were the result of a third-party cybersecurity test that was apparently improperly configured. Gemini reportedly didn’t retrieve any information from the systems it breached. On the heels of provocative disclosures from competitors OpenAI and Anthropic this summer, Google’s now the latest tech giant to confirm that its AI has hacked other companies.

Google has confirmed details in a Wall Street Journal report from last week that spelled out how Gemini models being tested by third-party cybersecurity firm Irregular erroneously made their way onto the open web and hacked into three companies’ servers in May. Per the reporting, Irregular set out to conduct a capture-the-flag test in which Gemini models were instructed to retrieve specific information from a fake company. The tests were meant to be in a closed environment, isolated to Irregular’s own severs.