Google’s consumer
Google says Gemini AI model breached real systems in security test
model Gemini hacked multiple systems through guessing login credentials, the company said, the latest case of rogue AI
scmp.com
Publisher
Sep 19, 2026 at 4:02 AM UTC · Updated il y a une heure · 1 min de lecture
AI
model Gemini hacked multiple systems through guessing login credentials, the company said, the latest case of rogue AI
cybersecurity
transgressions, which have generated safety concerns.
The hacks, first reported by the Wall Street Journal, took place in May and were discovered by
Google
in July.
“In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,” Heather Adkins, Google’s vice-president of security engineering, said in a statement on Friday.
The hacks happened during the same tests run by the AI security vendor Irregular that led to breaches previously disclosed by OpenAI, Anthropic and
Meta Platforms
.
Sourced by
Originally reported by scmp.com
NewsLayer coverage based on externally reported material.
The Daily Brief
The onchain economy, before your day starts.
Curated markets, onchain insights, and key headlines — delivered every weekday morning.
Weekdays · Free · ~5 minute read
0
Applause
Was this article helpful?
Article Intelligence
Topics
Related Coverage
Artificial IntelligenceCybersecurity researchers gain access to OpenAI’s GitHub repository using Claudeil y a 9 heures · 3 min read
Artificial IntelligenceGoogle's Gemini becomes latest AI model to break out and hack computer systemsil y a 6 heures · 2 min read
Artificial IntelligenceGoogle Gemini AI model hacks three other companiesil y a 5 heures · 2 min readSponsored
Ad
NewsLayerLearn more
NewsLayer Premium
Unlock deeper intelligence.
Ad-free reading, exclusive research, and real-time onchain insights.
Go Premium
