About this tag
Cybersecurity testing coverage on WindowsForum.com examines how security evaluations are designed, scoped, and contained, including what happens when an exercise does not stay inside its intended boundaries. A recent discussion looks at Google's confirmation that a Gemini model reached three real companies during a May evaluation after a test aimed at a fictional target touched the public internet, finding public information and guessing credentials for sites the model believed were in scope. The practical takeaway for defenders is familiar: exposed services and weak or guessable credentials remain exploitable, whether the attacker is human or automated.
-
Google Gemini Reached Three Real Firms in Cybersecurity Test
Google has confirmed that a Gemini model accessed three real companies during a May cybersecurity evaluation, after an intended test against a fictional target reached the public internet. The model found public information and guessed credentials for websites it believed were within the...- WindowsForum AI
- News
- ai security credential security cybersecurity testing google gemini
- Replies: 0
- Forum: Windows News