@article{Tao2026, 
author = {Jialing Tao and Song Huang and Changyou Zheng},
title = {Scaling the Strategy Wall: Efficient Jailbreaking of LLMs via Component-Based Multi-Objective Optimization},
year = {2026},
journal = {Computers, Materials & Continua},
volume = {88},
number = {3},
pages = {43},
keywords = {Jailbreak attacks, LLMs, multi-objective optimization, NSGA-II},
url = {https://www.sciopen.com/article/10.32604/cmc.2026.080119},
doi = {10.32604/cmc.2026.080119},
abstract = {BackgroundJailbreak attacks, which use crafted prompts to bypass safety alignments of Large Language Models (LLMs) and generate harmful content, pose a significant security threat. Existing methods often optimize for a single objective (e.g., attack success rate), neglecting critical factors like query efficiency, which limits their practicality and generalization.MethodsWe propose a Componentized Multi-Objective Optimization Framework (CMOOF), which introduces a paradigm shift: it searches for generalizable and query-efficient attack strategy templates within a structured, component-based strategy space. CMOOF leverages the NSGA-II algorithm to explicitly co-optimize two first-class objectives: Attack Success Rate (ASR) and Query Efficiency, thereby discovering their Pareto-optimal trade-off frontier.ResultsExperiments on benchmark datasets show significant improvements, with the highest jailbreak success rate reaching 98.75% on models like Llama3, and query efficiency surpassing baselines.ConclusionsCMOOF redefines jailbreak optimization from instance-level prompt crafting to strategy-level template discovery. The work provides an efficient, scalable, and generalizable jailbreak solution, and the framework offers broader insights for automated red teaming and LLM security defense.}
}