Trending
- Google’s Gemini AI Broke Into 3 Real Companies | AI Cyberattack
- Push Grows for ECOWAS-Wide AI Rules to Protect Electoral Integrity
- NairaRefinery AI Investment Platform Promises Unrealistic Returns is a Scam
- Viral Image Claiming APC Supporters’ Filling Stations Sell Petrol at ₦250 Is AI-Generated
- OpenAI Discloses Six Troubling AI Incidents as It Introduces New Safety Reporting Framework
- Nigeria and Chad Deepen Digital Partnership on Fibre Connectivity, AI
- FG Opens Digital Academy to Train 32000 Nigerians in AI, Cybersecurity
- Will AI Really Wipe Out Humanity? The 8 AI Risk Scenarios Nigerians Should Understand
Author: Lawrence Orjime
Lawrence Orjime
Lawrence Orjime is an AI and technology writer at AIBase.ng, covering the latest developments in artificial intelligence, emerging technologies, and the companies shaping the future of AI. With a background in content strategy, SEO, and digital media, Lawrence Orjime combines technology reporting with a strong understanding of what makes information useful and discoverable online.
Google has confirmed that its Gemini model gained unauthorised access to systems at three real companies during a Google Gemini cybersecurity test in May, after the evaluation environment unexpectedly allowed the model to reach the public internet. The company said the activity took place during an assessment of Gemini’s cybersecurity capabilities by Irregular, an independent firm that evaluates advanced AI systems. Google said this is the first publicly known case of one of its AI systems independently reaching real company systems in this way. How the Google Gemini cybersecurity test went beyond its intended target The exercise was designed as…