Gate AI: LLM Security Benchmark Evaluation Methodology and Results

Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses both. The detector under evaluation is scored...

EUVD-2022-55289

Malicious code in bioql PyPI...

PT-2024-10826 · Linux · Linux Kernel

Name of the Vulnerable Software and Affected Versions: Linux kernel affected versions not specified Description: A slab out-of-bounds issue was found in the Linux kernel, specifically in the thermal/drivers/cpufreq cooling module. This issue is scanned by KASAN in cpu power to freq. If power is...