Security News > 2024 > May > Researchers Uncover 'LLMjacking' Scheme Targeting Cloud-Hosted AI Models
2024-05-10 07:41
Cybersecurity researchers have discovered a novel attack that employs stolen cloud credentials to target cloud-hosted large language model (LLM) services with the goal of selling access to other threat actors. The attack technique has been codenamed LLMjacking by the Sysdig Threat Research Team. "Once initial access was obtained, they exfiltrated cloud credentials and gained
News URL
https://thehackernews.com/2024/05/researchers-uncover-llmjacking-scheme.html
Related news
- Apple Opens PCC Source Code for Researchers to Identify Bugs in Cloud AI Security (source)
- Researchers Discover Severe Security Flaws in Major E2EE Cloud Storage Providers (source)
- Researchers Reveal 'Deceptive Delight' Method to Jailbreak AI Models (source)
- Apple creates Private Cloud Compute VM to let researchers find bugs (source)
- Researchers Uncover Vulnerabilities in Open-Source AI and ML Models (source)
- How AI Is Changing the Cloud Security and Risk Equation (source)
- Google Cloud Cybersecurity Forecast 2025: AI, geopolitics, and cybercrime take centre stage (source)
- Researchers Warn of Privilege Escalation Risks in Google's Vertex AI ML Platform (source)