Low
Unverified
Google’s Gemini AI carried out cyberattacks, guessed passwords
Google has confirmed its Gemini AI model carried out cyberattacks in May by guessing login credentials to access multiple systems during a test.
Make your preference count — choose Punch.Add Punch on Google Google’s Gemini AI carried out cyberattacks, guessed passwords
Technology
September 19, 2026 6:39 am
File photo: Gemini
Agency Report
Kindly share this story:
•
•
•
•
•
•
Google’s consumer AI model Gemini hacked multiple systems through guessing login credentials, the company told AFP on Friday, 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, told AFP in a statement.
“In all three of these instances, the model stopped,” Adkins added, without specifying which organizations were breached.
“We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes.”
• AI operation uncovered 126 terror suspects – INTERPOL
• AI can’t replace special effects — Hakeem Onilogbo
• CDS urges military to embrace AI
In July, two OpenAI models escaped the closed environment they were meant to stay in, got onto the internet on their own and broke into the internal systems AI platform Hugging Face.
The incident fed worries that AI giants cannot keep their own models under control, as similar episodes have been reported at Anthropic and China’s Moonshot AI.
“These events highlight the importance of training powerful AI models to act responsibly,” Adkins emphasized.
AFP
Kindly share this story:
•
•
•
•
•
•
All rights reserved. This material, and other digital content on this website, may not be reproduced, published, broadcast, rewritten or redistributed in whole or in part without prior express written permission from PUNCH.
Contact: [email protected]
See more Punch stories on Google.Add Punch on Google
Stay informed and ahead of the curve! Follow The Punch Newspaper on WhatsApp for real-time updates, breaking news, and exclusive content. Don't miss a headline – join now!
Join The Punch Newspapers Channel
Stay in the know—fast. Get instant alerts, breaking headlines, and exclusive stories with the Punch News App. Download now and never miss a beat.
Get the Punch News App
Technology
September 19, 2026 6:39 am
File photo: Gemini
Agency Report
Kindly share this story:
•
•
•
•
•
•
Google’s consumer AI model Gemini hacked multiple systems through guessing login credentials, the company told AFP on Friday, 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, told AFP in a statement.
“In all three of these instances, the model stopped,” Adkins added, without specifying which organizations were breached.
“We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes.”
• AI operation uncovered 126 terror suspects – INTERPOL
• AI can’t replace special effects — Hakeem Onilogbo
• CDS urges military to embrace AI
In July, two OpenAI models escaped the closed environment they were meant to stay in, got onto the internet on their own and broke into the internal systems AI platform Hugging Face.
The incident fed worries that AI giants cannot keep their own models under control, as similar episodes have been reported at Anthropic and China’s Moonshot AI.
“These events highlight the importance of training powerful AI models to act responsibly,” Adkins emphasized.
AFP
Kindly share this story:
•
•
•
•
•
•
All rights reserved. This material, and other digital content on this website, may not be reproduced, published, broadcast, rewritten or redistributed in whole or in part without prior express written permission from PUNCH.
Contact: [email protected]
See more Punch stories on Google.Add Punch on Google
Stay informed and ahead of the curve! Follow The Punch Newspaper on WhatsApp for real-time updates, breaking news, and exclusive content. Don't miss a headline – join now!
Join The Punch Newspapers Channel
Stay in the know—fast. Get instant alerts, breaking headlines, and exclusive stories with the Punch News App. Download now and never miss a beat.
Get the Punch News App
Original reporting source
The Punch Nigeria
Read original report
Global News Alert provides an editorial summary and links readers to the original publisher.