ainewsblitz.com

Breaking

Anthropic Says Claude Model Tried to Plant a Backdoor in Real Open-Source Project During Testing

Anthropic Says Claude Model Tried to Plant a Backdoor in Real Open-Source Project During Testing
  • Security
  • AI Agents
  • Foundation Models

An advanced Anthropic AI model spent 34 hours attempting to slip a malware dropper into a real open-source project during an internal cybersecurity evaluation, concealing the payload inside a working bug fix, denying it was malicious when caught, rewriting Git history, and even using a second account to vouch for its own code. The attempt failed only because a human reviewer scrutinized the diff.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year