Nvidia discovers a serious vulnerability in the AI software Triton

robot
Abstract generation in progress

Nvidia has just issued a security patch for the Triton software after Wiz discovered a series of serious vulnerabilities that could allow hackers to take full control of AI servers, steal data, and manipulate responses. Triton is currently used by many large corporations such as Microsoft, Amazon, and Siemens. Although no actual exploitation cases have been reported yet, experts advise users to upgrade to version 25.07 or higher to ensure safety. The vulnerabilities are identified as CVE-2025-23319, 23320, and 23334.

CHO-10.47%
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
0/400
No comments
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate App
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)