zakky8/llm-jailbreak-taxonomy

Mechanism-grounded taxonomy of 40 LLM jailbreak patterns across 10 categories. 8,000-trial bootstrap evaluation for the June 2026 frontier (Claude Opus 4-8, GPT-5.5, Gemini 3.5, DeepSeek V4). Every citation direct-WebFetch verified; refuted claims documented.

语言：Jupyter Notebook · GitHub 星标：19 · Fork：0

话题：adversarial-attacks · adversarial-ml · adversarial-testing · ai-red-teaming · ai-safety · ai-security · alignment · jailbreak

在 GitHub 上查看原仓库