Research
Safety's Cybersecurity Intelligence Team conducts industry-leading research into security best practices, software supply chain vulnerabilities, and novel attack vectors.
Safety CLI Team Uncovers Unpublished Vulnerability in TensorFlow: CVE-2023-33976
The Safety CLI Cybersecurity Intelligence team discovered an unpublished vulnerability (CVE-2023-33976) in the TensorFlow Python package. This vulnerability, although fixed in TensorFlow version 2.13.0, remained unnoticed until its recent publication in July 2024, posing a hidden risk for many machine learning applications.
Read post
Open Post