A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities across Clinical Specialties

Medical Large Language Models LLMs are increasingly deployed for clinical decision support across diverse specialties, yet systematic evaluation of their robustness to adversarial misuse and privacy leakage remains inaccessible to most researchers. Existing security benchmarks require GPU cluster...

CVE-2021-35033

A vulnerability in specific versions of Zyxel NBG6818, NBG7815, WSQ20, WSQ50, WSQ60, and WSR30 firmware with pre-configured password management could allow an attacker to obtain root access of the device, if the local attacker dismantles the device and uses a USB-to-UART cable to connect the...