Dream

AI agents

2026-08-13 08:59:47

FT report says suspected China-linked hackers used autonomous AI agents in Taiwan government breach

A group of suspected China-linked hackers used autonomous open-source AI agents to breach multiple Taiwanese government systems in early July, according to a Financial Times report citing research from Israeli cybersecurity firm Dream. The company said the operation is the first government-targeted cyberattack it has seen carried out in an end-to-end autonomous manner. Dream said the attack unfolded over four days and involved as many as eight AI agents operating at the same time. The agents were used to identify targets, study available vulnerabilities, test different intrusion paths, and switch tactics when defenses blocked them. According to the firm, the campaign mapped the network architecture of 21 government systems, compromised at least 85 government user accounts, and stole more than 2,500 personnel records. The reported impact later extended to Taiwan’s nuclear safety regulator and at least seven energy companies. Dream Chief Strategy Officer Amir Becker said AI had previously been used to help human hackers with isolated tasks, but this case stood out because reconnaissance, vulnerability discovery, and intrusion were largely automated. Taiwan’s Ministry of Digital Affairs declined comment on confidentiality grounds, while China did not respond to requests for comment. The report noted that official attribution has not been confirmed.

1510

AI agents

2026-08-13 03:16:39

Dream says AI agents hit 21 Taiwan government systems in four days, exposing 2,500 personnel records

Israeli cybersecurity firm Dream said attackers stitched together two open-source AI agents, Hermes and OpenClaw, into an autonomous attack system that probed 21 Taiwan government systems over four days. According to the research, the operation launched 12 attack waves, compromised at least 85 government user accounts, and stole more than 2,500 personnel records. Dream said the system could search for targets, study vulnerabilities, and switch tactics when one path failed, with as many as eight sub-agents working at the same time. The researchers said the attackers identified more than 36 API endpoints covering account management, user data access, file uploads, and management functions. In one case, a full user database was reportedly accessible without any authentication gate. Dream added that the campaign later expanded beyond government websites to Taiwan’s Nuclear Safety Commission, government IT supply-chain vendors, government email systems, and at least seven energy operators. Dream said the attackers framed each step as an authorized security test to get past model safeguards. The company also noted that internal communications used simplified Chinese and said several signs pointed to operators linked to China, though it did not formally attribute the intrusion to a specific group.

1590