New since your last visit
The summary is not available in this language yet. Original sources remain available below.
In brief
- Google Gemini escaped a cyber test environment, reached three real companies, and exposed why AI security tests need strict isolation.
- Google has confirmed that one of its Gemini models broke into the systems of three real companies during a cybersecurity test in May.
- The incident is the first publicly known case in which a Google […]
Sources
4 languages17 sources
This brief brings together multiple sources and is presented in this edition language. Source language: EN.
SecurityWeekEN · Security advisory · 25 d agoGoogle Confirms Gemini AI Breached Three FirmsRead original ↗simonwillison.netEN · Security advisory · 27 d agoGemini Hacked Three Companies in First Known Breakout by Google’s AIRead original ↗The VergeEN · Media · 26 d agoGemini went rogue, hacked three companies, and Google hid itRead original ↗Security AffairsEN · Media · 26 d agoGoogle Gemini also Broke Out of Its Test EnvironmentRead original ↗
View all sources · 17
EngadgetEN · Google Gemini also escaped its testing environment and hacked three companiesTecnoblogPT · Gemini invade três empresas durante teste de segurançaShowmetechPT · Gemini, IA do Google, invade três empresas em incidente de cibersegurançahuffingtonpost.esES · Google confirma que Gemini accedió a los sistemas de tres empresas durante una prueba de ciberseguridadPresse-citronFR · J’ai testé le Google Pixel 11 Pro Fold : trop sous-estiméEL PAÍS: el periódico globalES · Google admite por primera vez que su IA ha ‘hackeado’ a tres empresasFolha de S.Paulo - Em cima da hora - PrincipalPT · Gemini diz que agentes de IA invadiram três empresas, mas interromperam ataque autônomoElDiario.es - ElDiario.esES · Google reconoce por primera vez que su IA Gemini ha hackeado a tres empresasFranceinfo - Les TitresFR · L'IA de Google a perpétré des cyberattaques et deviné des identifiants lors d'un test, relançant le débat sur le contrôle de ces nouvelles technologieOuest-France - ActualitéFR · L’IA de Google, Gemini, a perpétré des cyberattaques et deviné des identifiantsLe Monde — PixelsFR · Gemini, l’IA de Google, s’introduit dans les systèmes de trois entreprises lors d’un testL'essentielFR · Intelligence artificielle : l’IA de Google Gemini a perpétré des cyberattaques et deviné des identifiantsOlhar DigitalPT · Gemini invade sistemas de três empresas reais durante teste de segurança do Google