None
EN
Meta blames ‘misconfiguration’ after AI model hacked another company in security evaluation
['Santosh Kumari', '.Wp-Block-Gamurs-Author-Drawer__Wrapper Display Grid Grid-Template-Columns Height', 'Overflow-Y Scroll Position Fixed Right Top Transition Transform Ease-Out Width Z-Index -Ms-Overflow-Style None Scrollbar-Width None .Wp-Block-Gamurs-Author-Drawer__Wrapper', '-Webkit-Scrollbar Display None .Wp-Block-Gamurs-Author-Drawer__Wrapper.Bg-Minimal Background-Color Var --Wp--Custom--General-Color-Bg--Minimal', '.Wp-Block-Gamurs-Author-Drawer__Wrapper.Bg-Subtle Background-Color Var --Wp--Custom--General-Color-Bg--Subtle', '.Wp-Block-Gamurs-Author-Drawer__Wrapper.Bg-Bold Background-Color Var --Wp--Custom--General--Color-Bg--Bold', '.Wp-Block-Gamurs-Author-Drawer__Wrapper.Bg-Strong Background-Color Var --Wp--Custom--General-Color-Bg--Strong', '.Wp-Block-Gamurs-Author-Drawer__Wrapper.Bg-Sponsored Background-Color Var --Wp--Custom--General-Color-Bg--Sponsored', '.Wp-Block-Gamurs-Author-Drawer__Wrapper.Is-Visible Transform Translatex', '.Wp-Block-Gamurs-Author-Drawer__Inner-Wrapper Border-Radius Calc Var --Wp--Custom--General-Container--All-Devices--Border-Radius']
Attack of the Fanboy
This time, Meta said one of its AI models managed to hack into another organization’s systems during a controlled evaluation.
Those cases also involved AI models gaining unauthorized access to external systems during security testing.
The repeated incidents have sparked concerns about how AI evaluations are conducted and whether stronger safeguards are needed.
It’s getting a little unsettling that this keeps happening during AI testsMeta said the incident happened during an independent security evaluation carried out by AI security company Irregular.
Meta added that the situation was similar to other recently reported incidents involving AI testing.