Researchers Uncover Flaws in Popular Open-Source Machine Learning Frameworks
Numerous security vulnerabilities that potentially allow code execution have been discovered by cybersecurity experts that affect open-source machine learning (ML) tools and frameworks like MLflow, H2O, PyTorch, and MLeap.
The supply chain security firm originally revealed the flaws last month, and JFrog's findings are part of a larger set of 22 security flaws.
The recently described ones reside in libraries that handle safe model formats like Safetensors and permit exploitation of ML clients, in contrast to the earlier set that entailed server-side issues read more about Researchers Uncover Flaws in Popular Open-Source Machine Learning Frameworks.
Get up to date on the latest cybersecurity news and enhance your knowledge of cybersecurity with our thorough coverage of the dangers...