Browsing: hacked

The Wall Street Journal reported on Friday that Google has confirmed that a Gemini instance was able to leave its sandbox and attack other companies during a security test back in May. The company running the test was frontier AI security firm Irregular—which the Journal noted just so happens to have been involved in similar…

A small boat assigned to the Legend-class national security cutter USCGC Bertholf (WMSL 750) approaches the cutter for recovery following small boat operations in the Timor Sea, Sept. 9, 2026. (U.S. Coast Guard photo by Petty Officer 3rd Class Trinity Whalen)

Hiring new people and onboarding them is a part of life for growing businesses. Unfortunately, too often a new employee’s first password is also a security incident waiting to happen. 

Florida officials say an international cybercriminal group breached a driver-record database using compromised police credentials

Florida’s Department of Highway Safety and Motor Vehicles (FLHSMV) said Friday that it’s investigating a data breach, making it the second organization that hosts Americans’ driver’s license information to be hacked this month.

ByClare Duffy Thursday, September 3, 2026 2:22PM Nvidia announced that it will buy AI startup Hugging Face for $12.9 billion, a massive bet by the chipmaker to expand the reach of open-

In July, OpenAI admitted that one of its agents tasked with completing a cybersecurity experiment broke out of containment and hacked AI dataset platform Hugging Face. That incident, which got a full accounting from OpenAI yesterday, was the first publicly reported case where an LLM went rogue and autonomously hacked a third party. 

AI agents created by OpenAI broke into the company’s own systems during internal tests and in some cases tried to conceal their behavior, the company said in a report published Wednesday.

AI agents spun up by OpenAI broke into its own networks during tests gone wrong, the company said in a report published Wednesday.

We first noticed a ransomware family called StopAndProtect in the middle of May 2026. Further analysis of the infrastructure reveals that the infection chain starts with a ClickFix social-engineering technique, which prompts victims to execute a PowerShell command. This leads to two stages of additional downloaders and loaders written in .NET, followed by several main…