💻 Technology 1d ago

Poetry is the new AI security threat as PoeLLM malware infects 3K+ servers

The Register
Biting commentary and tech news from the UK
View Channel →
Poetry is the new AI security threat as PoeLLM malware infects 3K+ servers
Source ↗ 👁 0 💬 0
A suspected Italian attacker armed with a malware-controlling poem has infected more than 3,000 servers since April, breaking into enterprise AI infrastructure to mine cryptocurrency and add compromised systems to its growing botnet. This is the first case of “adversarial poetry” - an AI jailbreak technique that turns harmful prompts into poems to trick LLMs into bypassing safety guardrails - that Lumen’s Black Lotus Labs, which has been tracking the PoeLLM malware, has seen in real-world attack

Comments (0)

Sign in to join the discussion

More Like This

📰
New AI Agent Resources Proposed For The Linux Kernel, AI Skills To Help Developers
Phoronix · 5h ago
📰
Valve Lands VK_AMD_anti_lag Support For AMD RADV Driver In Mesa 26.3
Phoronix · 5h ago
Anthropic launches critical infrastructure program and free OSS Scanner for open source
SiliconANGLE · 7h ago
US disrupts Chinese hacking tools as 7 govts warn of PRC spies stealing sensitive data worldwide
www.theregister.com - Articles · 8h ago
Alphabet spinoff Isomorphic Labs reportedly raising funding at up to $50B valuation
SiliconANGLE · 8h ago
Nvidia found $1B under the couch to help secure American scientific computing dominance
www.theregister.com - Articles · 8h ago