A crypto-mining campaign involving malicious models on Hugging Face has resurfaced, days after its initial takedown. These models are designed to hijack GPU servers and install backdoors, with one such model being downloaded over 28,000 times. Additionally, a separate security threat involves a fake Solana starter kit on GitHub that aims to trick AI coding agents into installing NetSupport RAT. AI
IMPACT Malicious AI models are being used to hijack computing resources and distribute malware, posing a significant risk to developers and infrastructure.
RANK_REASON The cluster describes a security threat involving malicious models on a platform, which falls under the 'tool' category as it relates to the misuse of AI tools.
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →