Researchers have concocted a new way of manipulating machine learning (ML) models by injecting malicious code into the process of serialization. The method focuses on the "pickling" process used to ...

Google fixed a Vertex AI SDK flaw in v1.148.0 after Unit 42 showed bucket squatting could enable model hijacking and code ...

A new campaign exploiting machine learning (ML) models via the Python Package Index (PyPI) has been observed by cybersecurity researchers. ReversingLabs said threat actors are using the Pickle file ...

Google reportedly patched a flaw in the Vertex AI SDK for Python that could allow attackers to hijack model uploads and ...