SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.09113 · 2024

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), which has been shown to successfully jailbreak multiple open-source LLMs. Drawing inspiration from the difficulties of discrete token optimization, our method relaxes the discrete jailbreak optimization into a continuous optimization process while gradually increasing the sparsity of the optimizing vectors. This technique effectively bridges the gap between discrete and continuous space optimization. Experimental results demonstrate that our method is more effective and efficient than state-of-the-art token-level methods. On Harmbench, our approach achieves the highest attack success rate on seven out of eight LLMs compared to the latest jailbreak methods. Trigger Warning: This paper contains model behavior that can be offensive in nature.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.09113")
get_code_for_paper("2405.09113")
have("2405.09113")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.09113.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.09113.svg)](https://syntology.ai/paper/2405.09113)

Connect an agent — have() is free.