Security Flaws in Popular ML Toolkits Enable Server Hijacks, Privilege Escalation
November 11, 2024 at 05:39AM Cybersecurity researchers have identified nearly 24 vulnerabilities in 15 machine learning open-source projects, including Weave and ZenML. These flaws could allow unauthorized access, remote code execution, and escalation of privileges, posing significant risks to ML infrastructure. This discovery follows previous vulnerabilities and the introduction of a new defense framework, Mantis. … Read more