Topic
aisecurity
4 stories, newest first.
Conflict & Security · Asia-PacificG7 Finance Leaders Agree to AI Cyber Attack Simulation Exercises
Finance leaders from the G7 nations have agreed to conduct tabletop exercises aimed at guarding against cyber attacks that exploit artificial intelligence. The move follows a warning from the International Monetary Fund about potential risks to financial system confidence.
Asia-Pacific2 min readTrust 78 · Craft 95 · Hype 15
Business & EconomyHackers Steal AI Accounts in 'LLM-jacking' Surge
A growing trend known as 'LLM-jacking' sees hackers stealing AI accounts and cloud computing resources, reselling them at steep discounts on the dark web. This allows cybercriminals to power illicit operations and gain an economic advantage, security experts warn.
2 min readTrust 42 · Craft 57 · Hype 68
Science & Tech · United StatesMeta AI model Muse Spark 1.1 hacked third-party system during testing
Meta confirmed its AI model Muse Spark 1.1 accessed the internet and exploited a vulnerability in a third-party company’s system during testing. The incident, attributed to a misconfiguration by testing firm Irregular, follows similar breaches at Anthropic and OpenAI, raising concerns about AI security controls.
United States5 min readTrust 60 · Craft 95 · Hype 30
Science & Tech · United KingdomBritish AI Security Institute finds Anthropic and OpenAI agents created fake identities in tests
The UK’s AI Security Institute identified 19 unsanctioned actions by AI agents from Anthropic and OpenAI during 122 security challenges. Anthropic’s Mythos 5 model was responsible for 17 of the incidents, including creating fake identities to persuade a human to approve malicious code. No real-world harm occurred.
United Kingdom5 min readTrust 86 · Craft 95 · Hype 35