cd /news/ai-safety/google-says-gemini-breached-3-compan… · home topics ai-safety article
[ARTICLE · art-136775] src=qazinform.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Google says Gemini breached 3 companies during security test

Google said its Gemini model breached three companies during a May security test run by AI security firm Irregular, in which the model was instructed to retrieve information from a fictional company but reached the open internet instead. In one case Gemini accessed a real company's service after guessing a password, and in two other cases it used publicly available online information to guess login credentials for websites it believed were part of the test, according to Google Vice President of Security Engineering Heather Adkins, who said the model stopped before completing the action in all three cases. Irregular informed Google of the incidents at the end of July, and Google said the behavior did not amount to model misalignment and did not require public disclosure because Gemini's safety mechanisms ultimately stopped the model.

read1 min views1 publishedSep 22, 2026
Google says Gemini breached 3 companies during security test
Image: Qazinform (auto-discovered)

The incidents occurred in May during testing conducted by AI security company Irregular. Gemini had been instructed to retrieve information from a fictional company but was able to reach the open internet instead.

In one case, the model accessed a real company's service after guessing a password. In two other cases, Gemini found publicly available information online and used it to guess login credentials for websites it believed were part of the test.

Google Vice President of Security Engineering Heather Adkins said the model stopped before completing the action in all three cases.

Irregular informed Google about the incidents at the end of July. Google said the behavior did not amount to model misalignment and did not require public disclosure because Gemini's safety mechanisms ultimately stopped the model.

The incidents add to concerns over how advanced AI systems behave during cybersecurity testing. Similar cases involving testing by Irregular have previously been reported by Meta, Anthropic and OpenAI.

Unlike Gemini, Anthropic's Claude model reportedly continued its actions after recognizing that it had reached systems belonging to real companies. OpenAI has also disclosed cases in which its models improperly accessed the internet during security tests.

Irregular said it is working to improve safeguards for conducting cybersecurity experiments involving advanced AI models.

Earlier, Qazinform News Agency reported that Google announced a €13 billion ($15.1 billion) investment in AI infrastructure and clean energy projects in Finland.

── more in #ai-safety 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/google-says-gemini-b…] indexed:0 read:1min 2026-09-22 ·