mlsanityData to 14 Oct 2026

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security

arXiv 2509.06807 ↗First posted 8 Sep 2025cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

As Large Language Models (LLMs) increasingly permeate human life, their security has emerged as a critical concern, particularly their ability to maintain harmless responses to malicious instructions. Although extensive methods have improved LLMs' security, they often lead to conservative, rejection-oriented responses that compromise practical usability. This presents a key challenge: how to advance the Pareto frontier between LLMs' usability and security, rather than necessitate a trade-off between them. To address this, we propose the MoGU framework, in which the intra-layer router dynamically allocates weights by sensing hidden states, thereby balancing the contributions of security-optimized and usability-optimized variants. Despite its initial potential, the MoGU framework faces limitations such as parameter redundancy and performance bottlenecks. To overcome these, we further propose an improved MoGU_v2 framework that establishes a tighter coupling between the routers and hidden states. In MoGU_v2, routers are embedded only in layers encoding highly classifiable security features, and backbone modules are activated during router optimization to enable bidirectional adaptation. MoGU_V2 exhibits strong adaptability and stable improvements across various series of LLMs, including mainstream LLMs serving as brains in various applications, on-device LLMs optimized for resource-constrained scenarios, and reasoning LLMs tailored for user interpretability. Meanwhile, even facing risks introduced by Instruction Fine-tuning, MoGU_v2 can easily restore security without compromising the task performance gains via a simple data-mix strategy. These comprehensive improvements highlight MoGU_V2 as a robust and versatile solution for mitigating security risks in real-world applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 61 of its 69 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

61 of 69 references.

References · 61

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  9. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  10. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  11. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  12. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
38 more
  1. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  2. 2023LIMA: Less Is More for Alignmentcited by 1,100
  3. 2022Red Teaming Language Models with Language Modelscited by 1,026
  4. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 785
  5. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  6. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 694
  7. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  8. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 431
  9. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  10. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 387
  11. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  12. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  13. 2024Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothingcited by 346
  14. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  15. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  16. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 257
  17. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decodingcited by 247
  18. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  19. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Surveycited by 230
  20. 2023LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Bcited by 195
  21. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  22. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 192
  23. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 191
  24. 2024OpenMoE: An Early Effort on Open Mixture-of-Experts Language Modelscited by 187
  25. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 175
  26. 2023Removing RLHF Protections in GPT-4 via Fine-Tuningcited by 171
  27. 2019Adaptive Attention Span in Transformerscited by 149
  28. 2025SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilitiescited by 136
  29. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  30. 2024Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Modelscited by 125
  31. 2024Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attackcited by 115
  32. 2023Explore, Establish, Exploit: Red Teaming Language Models from Scratchcited by 114
  33. 2024Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmeticcited by 112
  34. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 108
  35. 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Modelscited by 106
  36. 2024How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden Statescited by 98
  37. 2024Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbationcited by 92
  38. 2025The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1cited by 91

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sinkcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
  2. 2026Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection
  3. 2025OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models
  4. 2025Life-Cycle Routing Vulnerabilities of LLM Router
  5. 2026A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
  6. 2026Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
  7. 2026TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
  8. 2025MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents