rhavaei 的提交内容

A comprehensive analysis of Llama4 safety in CBRN tasks vs. closed-source models [pdf]

LLM Robustness/Safety Benchmark

An Implementation of AutoDAN Turbo

Using Deepseek R1 to Break LLMs: Tree of Attacks

The Jailbreak Bible

Red-Teaming ChatGPT for Hallucinations – Code and Report

Consistent Jailbreaking Method in o1, o3, and 4o

Jailbroken: Finding 50,000 Legal Hallucinations in GPT-4o with RL