Study finds Z.AI's GLM-5.3 can execute multi-stage cyberattacks

Evidence a frontier Chinese model can chain real attack steps raises agentic cyber-risk questions.

Researchers say Z.AI's GLM-5.3 model completed 3 of 13 complex cyberattack scenarios in Irregular's simulated tests, pointing to blind spots in AI safety reviews.

Domain

security

Read it at Reuters →

Coverage: 16 sources, in order

1. 29 Oct 03:28 Reuters Read the article →
2. 29 Oct 03:40 The Mighty 790 KFGO Read the article →
3. 29 Oct 03:44 Crypto Briefing Read the article →
4. 29 Oct 03:49 The Economic Times Read the article →
5. 29 Oct 03:49 The Economic Times Read the article →
6. 29 Oct 04:02 Modesto Bee Read the article →
7. 29 Oct 04:02 Sacramento Bee Read the article →
8. 29 Oct 04:08 شبكة تواصل الإخبارية Read the article →
9. 29 Oct 04:10 The Straits Times Read the article →
10. 29 Oct 04:13 FourWeekMBA Read the article →
11. 29 Oct 05:30 Free Malaysia Today Read the article →
12. 29 Oct 05:55 BigGo Finance Read the article →
13. 29 Oct 07:07 news.sbs.co.kr Read the article →
14. 29 Oct 07:07 news.sbs.co.kr Read the article →
15. 29 Oct 08:03 AsiaOne.com Read the article →
16. 29 Oct 10:27 IOL Read the article →

← Front page