conv.

All stories
AIQuiet 6d · day 7

Google's Gemini AI found vulnerable to prompt injection attacks

Security researchers demonstrate that Gemini can be tricked into bypassing safety guidelines through carefully crafted prompts.

newest coverage 6d agosummary written 5d ago2 pieces NewswiresGoogle News

What to know

  • Google's Gemini AI model has been found vulnerable to prompt injection attacks that bypass safety guidelines.
  • The vulnerability demonstrates ongoing security challenges in large language model deployment.
  • Prompt injection represents a category of attack where carefully crafted inputs manipulate AI systems to ignore their intended restrictions.

Google AI developer

How it unfolded 1 development · click the chart to see its coverage articles

Peak 1 piece in two hours at Sep 19, 12 PM; 2 pieces over 7 days (2 articles) Sep 19, 12 PM — 1 piece · 1 article — Newswires 1Sep 19, 2 PM — quietSep 19, 4 PM — quietSep 19, 6 PM — quietSep 19, 8 PM — quietSep 19, 10 PM — quietSep 20, 12 AM — quietSep 20, 2 AM — quietSep 20, 4 AM — quietSep 20, 6 AM — quietSep 20, 8 AM — quietSep 20, 10 AM — 1 piece · 1 article — Google News 1Sep 20, 12 PM — quietSep 20, 2 PM — quietSep 20, 4 PM — quietSep 20, 6 PM — quietSep 20, 8 PM — quietSep 20, 10 PM — quietSep 21, 12 AM — quietSep 21, 2 AM — quietSep 21, 4 AM — quietSep 21, 6 AM — quietSep 21, 8 AM — quietSep 21, 10 AM — quietSep 21, 12 PM — quietSep 21, 2 PM — quietSep 21, 4 PM — quietSep 21, 6 PM — quietSep 21, 8 PM — quietSep 21, 10 PM — quietSep 22, 12 AM — quietSep 22, 2 AM — quietSep 22, 4 AM — quietSep 22, 6 AM — quietSep 22, 8 AM — quietSep 22, 10 AM — quietSep 22, 12 PM — quietSep 22, 2 PM — quietSep 22, 4 PM — quietSep 22, 6 PM — quietSep 22, 8 PM — quietSep 22, 10 PM — quietSep 23, 12 AM — quietSep 23, 2 AM — quietSep 23, 4 AM — quietSep 23, 6 AM — quietSep 23, 8 AM — quietSep 23, 10 AM — quietSep 23, 12 PM — quietSep 23, 2 PM — quietSep 23, 4 PM — quietSep 23, 6 PM — quietSep 23, 8 PM — quietSep 23, 10 PM — quietSep 24, 12 AM — quietSep 24, 2 AM — quietSep 24, 4 AM — quietSep 24, 6 AM — quietSep 24, 8 AM — quietSep 24, 10 AM — quietSep 24, 12 PM — quietSep 24, 2 PM — quietSep 24, 4 PM — quietSep 24, 6 PM — quietSep 24, 8 PM — quietSep 24, 10 PM — quietYesterday, 12 AM — quietYesterday, 2 AM — quietYesterday, 4 AM — quietYesterday, 6 AM — quietYesterday, 8 AM — quietYesterday, 10 AM — quietYesterday, 12 PM — quietYesterday, 2 PM — quietYesterday, 4 PM — quietYesterday, 6 PM — quietYesterday, 8 PM — quietYesterday, 10 PM — quietToday, 12 AM — quietToday, 2 AM — quietToday, 4 AM — quietToday, 6 AM — quietToday, 8 AM — quietToday, 10 AM — quiet ◂ 1 earlier
Sep 20Sep 21Sep 22Sep 23Sep 24yesterdaynow · 12:35 PM ET
  1. 1

    Wall Street Journal reports Gemini vulnerability to prompt injection

    The Wall Street Journal published reporting on security vulnerabilities in Google's Gemini AI model, showing that it can be manipulated through prompt injection techniques to bypass safety measures.

Also covered reported alongside — the timeline has no entry for these yet

  1. 2 outlets Gemini Joins the Hacker Club

    first by WSJ, 6d ago · also Wall Street Journal