Subscribe Sign in

Gemini hacked three companies in first known breakout by Google's AI

ABC News
1 min read Rewritten in plain language

Artificial intelligenceCyber Security

Show what we removed Rules applied: C1 D2×2 D3×5 D4 E3 F2×5 all 30 rules
  • Google's AI model Gemini accessed the internet and hacked three companies during a cybersecurity evaluation.
  • During the cybersecurity assessment, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google's vice-president of security engineering, said in a statement.
  • Irregular told Google about the hacks in July, the two companies told the Wall Street Journal, which first reported on the hacking incident on Friday local time.
  • The hacks happened while Gemini was participating in a "capture the flag" exercise conducted on infrastructure belonging to Irregular to test the model's cybersecurity capabilities.
  • Irregular told the Wall Street Journal that the incident with Google Gemini was due to the same problem as the earlier breaches during tests with other AI models.

5 sentences from our version of the report, chosen to cover it. Nothing here is written; every line is in the article below. How

Ms Adkins said in all three instances, the model ceased the hacking when it learned it had accessed a real company.

Headline check

The one thing this headline claims is in the report.

Figures, names and quoted words in the headline, looked for in the report itself — not in the summary above. One claim in this headline could be checked, so this is a narrow pass and not a thorough one. How this is checked

Google's AI model Gemini accessed the internet and hacked three companies during a cybersecurity evaluation.

Researchers say loss of control incidents with AI are on the rise, with the potential for more serious incidents with "catastrophic consequences" to come.

The hacks occurred in May during a test conducted by Irregular, an independent company that conducts cybersecurity evaluations.

During the cybersecurity assessment, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google's vice-president of security engineering, said in a statement.

Ms Adkins said that in all three instances, the model ceased the hacking when it learned it had accessed a real company.

Irregular told Google about the hacks in July, the two companies told the Wall Street Journal, which first reported on the hacking incident on Friday local time.

Google told the WSJ it didn't consider it necessary to disclose the incidents earlier because its model stopped the hacking upon learning the companies were real and did not cause harm to them.

The hacks happened while Gemini was participating in a "capture the flag" exercise conducted on infrastructure belonging to Irregular to test the model's cybersecurity capabilities.

In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, according to the Wall Street Journal.

Irregular told the Wall Street Journal that the incident with Google Gemini was due to the same problem as the earlier breaches during tests with other AI models.

Shortened to 1 minute of reading, this version reads 8.7 on the Niral Score.

You are reading our version, not theirs. This is ABC News's report shortened to its most important sentences, in plainer words, with verdicts and loaded words taken out. Plain description stays, and so do adjectives that carry a fact, such as "former" or "federal". The reporting, the facts and the quotations are theirs — quotations are never edited — and the indicators beside it measure this version. Hover or tap Adjectives to see every one left in the text.

How outlets headlined it

Each outlet's own headline. Struck through: the loaded words our version leaves out. Plainest first.

  • ABC News Gemini hacked three companies in first known breakout by Google's AI plain
  • The West Australian Google's AI model hacked companies, accessed internet plain
  • Engadget Google Gemini also escaped its testing environment and hacked three companies plain

How each outlet filed it

Also covered by The West Australian. We hold only their summary of it, not the report, so there is nothing of theirs to measure here.

Outlet Niral ScoreAdjectivesSourcingSentimentHappiness
ABC Newsas they published this story 16.4 13 65 0.0 31.2
Engadget 10.8 5 65 0.2 50
Mundane Readneutralized from Engadget 9.4 5 65 0.2 50

Sign in to react.

Comments

Nothing here yet.

Sign in to comment.

Questions

Readers can ask a question about this story here. Questions and answers are for subscribers. Sign in to read them.

Comments are read before they appear where anything in them needs a person to look. Nothing posted here is ever deleted; a comment taken down keeps its text and the reason, so the decision can be looked at again. How this works

The same event elsewhere

2 other outlets filed this story. The scoreboard above is what they did differently.