mlsanityData to 14 Oct 2026

HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

arXiv 2510.18728 ↗First posted 21 Oct 2025cs.CR cs.AIcited by 4

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement; and a Network Traverser for real-time adaptive attack execution. HarmNet systematically explores and refines the adversarial space to uncover stealthy, high-success attack paths. Experiments across closed-source and open-source LLMs show that HarmNet outperforms state-of-the-art methods, achieving higher attack success rates. For example, on Mistral-7B, HarmNet achieves a 99.4% attack success rate, 13.9% higher than the best baseline. Index terms: jailbreak attacks; large language models; adversarial framework; query refinement.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 20 of its 26 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

20 of 26 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models16 Feb
  2. 2024MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue6 Nov
  3. 2024Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models15 Oct
  4. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
  5. 2024DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers25 Feb
  6. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  7. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  8. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 12

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Mistral 7Bcited by 3,164
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2023A Survey of Large Language Modelscited by 2,576
  7. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  8. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  9. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 245
  10. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
  11. 2022CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Modelscited by 53
  12. 2024Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectivescited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreakscited by 1
  2. 2026Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversationscited by 0
  3. 2026SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemescited by 0
  4. 2026PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
  2. 2026LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
  3. 2025GuardNet: Graph-Attention Filtering for Jailbreak Defense in Large Language Models
  4. 2025ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
  5. 2026Adversarial Reframing: A Framework for Targeted Generation in Language Models
  6. 2026MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
  7. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
  8. 2026SoK: Robustness in Large Language Models against Jailbreak Attacks