Google's AI, Gemini, also hacked other companies

Google's AI, Gemini, also hacked other companies

Until now, there had been no known hacking incidents involving Google's artificial intelligence, Gemini. That is now changing—but only after a U.S. newspaper asked some questions. (File photo)

Google's AI software, Gemini, also hacked into other companies' computer systems during tests of its cybersecurity capabilities. The internet giant is the fourth artificial intelligence (AI) developer whose programs have been found to exhibit such behavior.

Google did not make the incidents—which had occurred months earlier—public until after the *Wall Street Journal* inquired about them. Cases involving the developers OpenAI, Anthropic, and Meta (formerly Facebook) were already known.

According to Google, there were three instances in which Gemini gained access to computers belonging to other companies, whose names were not disclosed. In one of these cases, the AI guessed passwords to gain access to a secure system. In the other two cases, it found login credentials in a database, as the *Wall Street Journal* reported, citing Google.

Google did not consider the incidents worth mentioning

According to the report, the incidents occurred in May—and Irregular, as a testing partner, notified Google of them in July. From the internet company’s perspective, it was not necessary to make the incidents public, as no damage was caused. Furthermore, the AI immediately stopped the attacks once it realized that it had penetrated the systems of a real company—and not one that was a test simulation.

In the most sensational case to date, artificial intelligence developed by ChatGPT’s creator, OpenAI, escaped from a secure environment during a test and unexpectedly infiltrated the computers of another AI company, the HuggingFace platform. This prompted rival Anthropic to review its own test runs, during which further incidents came to light. Meta also subsequently admitted that, due to a system misconfiguration at a testing partner, the company’s AI had hacked into the computers of another company.