Summary of Codechameleon: Personalized Encryption Framework For Jailbreaking Large Language Models, by Huijie Lv et al.
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
by Huijie Lv, Xiao Wang, Yuansen Zhang, Caishuang Huang, Shihan Dou, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers investigate the threats posed by adversarial attacks on Large Language Models (LLMs), specifically “jailbreaking” that bypasses safety and ethical protocols. They propose a novel framework called CodeChameleon, which uses personalized encryption tactics to evade intent security recognition and guarantee response generation functionality. The authors conduct extensive experiments on 7 LLMs, achieving state-of-the-art average Attack Success Rate (ASR) with an impressive 86.6% ASR on GPT-4-1106. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about keeping Large Language Models safe from bad actors who try to trick them. The researchers found that these models can be “jailbroken” to do things they weren’t designed to do, like generate false information. They came up with a new way to keep the models safe by using secret codes and encryption. This helps prevent the bad guys from hacking into the model’s instructions. |
Keywords
» Artificial intelligence » Gpt
