LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen offsets in the leaf_depth_ buffer during feature contribution computation.
2026年9月17日
CVE-2026-92786 [HIGH] – LightGBM through 4.7.0 fails to validate child and split array values when parsing text mo
📑 文章目录



