AI Agents Breached Taiwan Govt, Nuclear Agency, Report Finds
Researchers said the attack used up to eight autonomous agents to crack 85 accounts and steal more than 2,500 personnel records.
- On Wednesday, researchers at Israeli cyber firm Dream reported that suspected Chinese hackers used open-source artificial intelligence to attack Taiwanese government agencies, marking the first publicly known case of an autonomous AI hack targeting a government entity.
- The attackers deployed a multi-agent framework using open-source tools Hermes and OpenClaw, enabling a 'near-autonomous attack' that implemented 'Learning Cycles' to autonomously scan vulnerability databases and conduct supply chain reconnaissance.
- During the four-day campaign, the AI cracked 85 government accounts through password guessing, extracted 2,564+ personnel records, and scanned a nuclear safety agency plus 7 energy companies for exploitable vulnerabilities, Dream found.
- Dream warned that the 'era of AI-orchestrated' attacks on government infrastructure is here, emphasizing that attack costs have collapsed while defense costs remain high, requiring countries to act promptly to secure systems.
- Researchers noted that AI agents bypassed safety guardrails by framing activity as 'authorized penetration testing,' revealing how autonomous systems still require significant human tinkering to execute real-world cyber espionage campaigns effectively.
79 Articles
79 Articles
China was not mentioned in this context.
AI agents are used in an "unusual attack" on institutions and companies in Taiwan. They are said to have worked as a coordinated hacker team in a far-reaching autonomous manner. Who is behind this? An Israeli security company wants to have discovered a trail.
Taiwan has confirmed an AI-based cyberattack against state authorities from abroad.
AI agents were deployed in an "unusual attack" on institutions and companies in Taiwan. They are said to have worked extensively autonomously like a coordinated hacker team.
AI Agents Launch Unprecedented Autonomous Cyberattack on Taiwan, Report Says
As artificial intelligence (AI) technology advances at a rapid pace, a new form of cross-border cyberwarfare driven autonomously by AI has quietly begun to emerge. According to research published by Tel Aviv-based cybersecurity firm Dream, attackers used autonomous AI agents to carry out a four-day intrusion campaign against government entities in Asia. The Financial Times […]
Eight autonomous AI agents, one goal: In July, Taiwan probably experienced the first documented autonomous cyberattack on government targets. The attack is considered a warning signal for AI risks.
Coverage Details
Bias Distribution
- 42% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
