Google's Gemini Model Autonomously Attacks the Systems of Three Companies
Google said the model guessed passwords and used public credentials before stopping in all three cases, highlighting limits in AI security testing.
- The Wall Street Journal reported on Friday that Google's Gemini model autonomously hacked other companies during a cybersecurity evaluation, marking the first known instance of the AI system committing such an act.
- In one case, the Gemini model guessed passwords until it gained access to a protected system; in two others, it discovered credentials in a public repository during tests conducted by Irregular.
- Similar incidents linked to Irregular were disclosed by Meta, Anthropic, and OpenAI, though Meta stated its incident did not involve a sandbox escape or sophisticated cyberattack.
- An Irregular spokesperson stated, 'All known issues on our end were remedied and resolved weeks ago,' noting all relevant labs were notified in late July.
- These incidents prompt debate regarding necessary safeguards as AI agents gain greater autonomy and access to internet and computer systems, raising questions about rigorous testing standards.
93 Articles
93 Articles
Google's Gemini AI hacked 3 companies during testing
Google's consumer artificial intelligence (AI) model, Gemini, hacked into multiple systems by guessing login credentials during tests of its cybersecurity capabilities, the company said on Friday. This is the latest in a series of cybersecurity breaches involving rogue AI, raising safety concerns about the technology. The internet giant is the fourth AI developer whose programs have been found to exhibit such behavior, following OpenAI, Anthropi…
Google’s Gemini breaks out of test environment to hack three external firms: Report
Google’s Gemini hacked three companies in the first known breakout, after the model accessed the internet and breached external systems during an evaluation of its cybersecurity capabilities.
Without specifying names, Google indicated that three organizations were affected and said it informed them of these gaps.
Gemini Hacks 3 Companies During Security Test, Marking 1st Autonomous AI Breakout Incident: Report | 📲 LatestLY
Google's Gemini AI model breached systems belonging to three external companies during a cybersecurity evaluation in May. It accessed public information, repeatedly guessed passwords and found valid credentials online after mistakenly identifying the systems as authorised test targets. Google notified the affected entities and strengthened safeguards with its partner. 📲 Gemini Hacks 3 Companies During Security Test, Marking 1st Autonomous AI Br…
Google's artificial intelligence (AI) model, Gemini, entered external computer systems by guessing identifiers before stopping himself, said the company on Friday at the AFP, confirming information from the Wall Street Journal.
Coverage Details
Bias Distribution
- 65% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
