NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks

Authors

Javad Rafiei Asl, Old Dominion UniversityFollow
Sidhant Narula, Old Dominion UniversityFollow
Mohammad Ghasemigol, Old Dominion UniversityFollow
Eduardo Blanco, University of Arizona
Daniel Takabi, Old Dominion UniversityFollow

Document Type

Conference Paper

Publication Date

2025

DOI

10.18653/v1/2025.emnlp-main.1235

Publication Title

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

Pages

24278-24306

Conference Name

2025 Conference on Empirical Methods in Natural Language Processing, November 4-9, 2025, Suzhou, China

Abstract

Large Language Models (LLMs) have revolutionized natural language processing, yet remain vulnerable to jailbreak attacks—particularly multi-turn jailbreaks that distribute malicious intent across benign exchanges, thereby bypassing alignment mechanisms. Existing approaches often suffer from limited exploration of the adversarial space, rely on hand-crafted heuristics, or lack systematic query refinement. We propose NEXUS (Network Exploration for eXploiting Unsafe Sequences), a modular framework for constructing, refining, and executing optimized multi-turn attacks. NEXUS comprises: (1) ThoughtNet, which hierarchically expands a harmful intent into a structured semantic network of topics, entities, and query chains; (2) a feedback-driven Simulator that iteratively refines and prunes these chains through attacker–victim–judge LLM collaboration using harmfulness and semantic-similarity benchmarks; and (3) a Network Traverser that adaptively navigates the refined query space for real-time attacks. This pipeline systematically uncovers stealthy, high-success adversarial paths across LLMs. Our experimental results on several closed-source and open-source LLMs show that NEXUS can achieve a higher attack success rate, between 2.1% and 19.4%, compared to state-of-the-art approaches. Our source code is available at https://github.com/inspire-lab/NEXUS.

Rights

© 2025 Association for Computational Linguistics.

Licensed on a Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Original Publication Citation

Asl, J. R., Narula, S., Ghasemigol, M., Blanco, E., & Takabi, D. (2025). NEXUS: Network Exploration for eXploiting Unsafe Sequences in multi-turn LLM jailbreaks. In C. Christodoulopoulos, T. Chakraborty, C. Rose, & V. Peng (Eds.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 24278-24306). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.1235

Repository Citation

Asl, J. R., Narula, S., Ghasemigol, M., Blanco, E., & Takabi, D. (2025). NEXUS: Network Exploration for eXploiting Unsafe Sequences in multi-turn LLM jailbreaks. In C. Christodoulopoulos, T. Chakraborty, C. Rose, & V. Peng (Eds.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 24278-24306). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.1235

ORCID

0000-0002-6154-1068 (Asl), 0009-0000-7998-7183 (Narula), 0000-0001-6661-0942 (GhasemiGol), 0000-0003-0447-3641 (Takabi)