Chinese AI model carries out complex cyberattacks in controlled tests, researchers say
The open-weight model also bypassed safeguards and reproduced forbidden code, underscoring concerns that it could lower barriers to sophisticated cyberattacks.
9 Articles
9 Articles
(Seoul = Yonhap News) Reporter Lee Seong-han = The latest model of Chinese artificial intelligence (AI) developer Z.AI (formerly ZipuAI) [tests] complex cyber attacks in a simulation environment...
Chinese AI model shows advanced hacking capabilities, raises security concerns
BEIJING: Chinese firm Z.AI's flagship AI model carried out complex cyberattacks in controlled simulations and repeatedly ignored instructions in separate tests, according to a report by AI security research firm Irregular.The GLM-5.3 model successfully completed 3 of 13 multi-stage cyberattack scenarios at least once, the strongest performance Irregular has recorded from an openly available AI model.GLM-5.3 still trails leading US models in Irre…
Chinese AI model carries out complex cyberattacks in controlled tests, researchers say
By Eduardo Baptista BEIJING, Oct 29 (Reuters) - Chinese firm Z.AI's flagship AI model carried out complex cyberattacks in controlled simulations and repeatedly ignored instructions in separate tests, according to a report by AI security research firm I...
GLM-5.3, Z.AI’s open weight model, completed at least once three of 13 simulated cyberattack scenarios and automated part of the tasks. Irregular also noted that it ignored instructions in separate tests, a signal that poses risks to the use of open systems.
Coverage Details
Bias Distribution
- 83% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
