Malicious attack method on hosted ML models now targets PyPI

A new malicious campaign has been discovered targeting the Python Package Index (PyPI) by exploiting the Pickle file format in machine learning models. Three malicious packages posing as an Alibaba AI Labs SDK were detected, containing infostealer payloads hidden inside PyTorch models. The packages exfiltrate information about infected machines and .gitconfig file contents. This attack demonstrates the evolving threat landscape in AI and machine learning, particularly in the software supply chain. The campaign likely targeted developers in China and highlights the need for improved security measures and tools to detect malicious functionality in ML models.

• LiteLLM supply chain compromiseCampaign2026-10-22
• ARTEX in the Wild: Storm-0940 Expands Targeting of IT and Software VendorsMalware2026-10-22
• LiteLLM PyPI Package and Docker Images Compromised to Steal Cloud and AI CredentialsMalware2026-10-21
• Two critical RCEs in PHP coreExploitedVulnerability2026-10-21
• How Tenable brought multi-language support to security detectors with agentic translationAnalysis2026-10-21