Summary of Gasp: Efficient Black-box Generation Of Adversarial Suffixes For Jailbreaking Llms, by Advik Raj Basani et al.
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
by Advik Raj Basani, Xiao Zhang
First submitted to arxiv on: 21 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
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 The paper introduces the Generative Adversarial Suffix Prompter (GASP), a novel framework that addresses limitations in existing jailbreak methods for Large Language Models (LLMs). GASP combines human-readable prompt generation with Latent Bayesian Optimization (LBO) to efficiently create adversarial suffixes, optimizing attack efficacy while maintaining prompt coherence. The framework leverages LBO to explore continuous embedding spaces and iteratively refine prompts. Experimental results show that GASP generates natural jailbreak prompts, improving attack success rates and reducing training times. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models can be tricked into giving bad answers by cleverly designed prompts. Researchers have developed ways to make these prompts, but they often don’t work well or take a long time. The new Generative Adversarial Suffix Prompter (GASP) is better at making these prompts and does it quickly and efficiently. |
Keywords
* Artificial intelligence * Optimization * Prompt
