Accès ouvert · CC BY

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

Résumé

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 github.com/inspire-lab/NEXUS.

Citer ce document

Asl, J. R., Narula, S., GhasemiGol, M., Blanco, E., & Takabi, D. (2025). NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks. https://doi.org/10.18653/v1/2025.emnlp-main.1235

Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)

Accès au document

Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter

Voir l'article sur le site de la revue

Licence et provenance

Licence : CC BY

Notice moissonnée depuis OpenAlex le 28/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →

Statistiques

Consultations (hors robots) : 13

Téléchargements (hors robots) : 0

Méthode de comptage