ResearchTrend.AI
  • Communities
  • Connect sessions
  • AI calendar
  • Organizations
  • Join Slack
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2026 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2504.18564
276
5
v1v2 (latest)

DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization

21 April 2025
Xinzhe Huang
Kedong Xiu
T. Zheng
Churui Zeng
Wangze Ni
Zhan Qiin
K. Ren
Chong Chen
    AAML
ArXiv (abs)PDFHTMLGithub (3★)
Main:13 Pages
7 Figures
Bibliography:2 Pages
Appendix:3 Pages
Abstract

Recent research has focused on exploring the vulnerabilities of Large Language Models (LLMs), aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting both LLMs and Guardrails, the effectiveness of existing attacks is limited when attempting to bypass safety-aligned LLMs shielded by guardrails. Therefore, in this paper, we propose DualBreach, a target-driven framework for dual-jailbreaking. DualBreach employs a Target-driven Initialization (TDI) strategy to dynamically construct initial prompts, combined with a Multi-Target Optimization (MTO) method that utilizes approximate gradients to jointly adapt the prompts across guardrails and LLMs, which can simultaneously save the number of queries and achieve a high dual-jailbreaking success rate. For black-box guardrails, DualBreach either employs a powerful open-sourced guardrail or imitates the target black-box guardrail by training a proxy model, to incorporate guardrails into the MTO process.

View on arXiv
Comments on this paper