NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs

• URL: http://arxiv.org/abs/2508.09473v1
• Date: Wed, 13 Aug 2025 04:05:28 GMT
• Title: NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
• Authors: Birong Pan, Mayi Xu, Qiankun Pi, Jianhao Chen, Yuanyuan Zhu, Ming Zhong, Tieyun Qian,
• Abstract summary: We propose NeuronTune, a fine-grained framework that dynamically modulates sparse neurons to achieve simultaneous safety-utility optimization.<n>Our approach first identifies safety-critical and utility-preserving neurons across all layers via attribution, then employs meta-learning to adaptively amplify safety-neuron activations and suppress utility-neuron activations.
• Score: 19.133502330591092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness against malicious attacks, frequent refusal of benign queries, degradation in generated text quality and general task performance--the former two reflecting deficits in robust safety and the latter constituting utility impairment. We trace these limitations to the coarse-grained layer-wise interventions in existing methods. To resolve this, we propose NeuronTune, a fine-grained framework that dynamically modulates sparse neurons to achieve simultaneous safety-utility optimization. Our approach first identifies safety-critical and utility-preserving neurons across all layers via attribution, then employs meta-learning to adaptively amplify safety-neuron activations and suppress utility-neuron activations. Crucially, NeuronTune enables tunable adjustment of intervention scope via neuron-count thresholds, supporting flexible adaptation to security-critical or utility-priority scenarios. Extensive experimental results demonstrate that our method significantly outperforms existing state-of-the-art technologies, achieving superior model safety while maintaining excellent utility.

Related papers

• Robust Spiking Neural Networks Against Adversarial Attacks [49.08210314590693]
  Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing.<n>In this study, we theoretically demonstrate that threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs.<n>We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances.
  arXiv  Detail & Related papers  (2026-02-24T05:06:12Z)
• Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models [57.006252510102506]
  Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications.<n>We introduce a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems.
  arXiv  Detail & Related papers  (2026-02-12T22:03:35Z)
• SafeNeuron: Neuron-Level Safety Alignment for Large Language Models [71.50117566279185]
  We propose SafeNeuron, a neuron-level safety alignment framework that improves robustness by redistributing safety representations across the network.<n>In experiments, SafeNeuron significantly improves robustness against neuron pruning attacks, reduces the risk of open-source models being repurposed as red-team generators, and preserves general capabilities.
  arXiv  Detail & Related papers  (2026-02-12T16:40:05Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks [12.216665194706708]
  We propose the Fine-Grained Safety Neurons (FGSN) with Training-Free Continual Projection method to reduce the fine-tuning safety risks.<n>FGSN inherently integrates the multi-scale interactions between safety layers and neurons, localizing sparser and more precise fine-grained safety neurons.
  arXiv  Detail & Related papers  (2025-08-08T03:20:25Z)
• Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision [0.716879432974126]
  This paper bridges the gap between theoretical guarantees and real-world implementations by incorporating robustness under finite-precision perturbations.<n>We employ state-of-the-art mixed-precision fixed-point tuners to synthesize sound and efficient implementations, thus providing a complete end-to-end solution.<n>We evaluate our approach on case studies from the automotive and aeronautics domains, producing efficient NN implementations with rigorous infinite-time horizon safety guarantees.
  arXiv  Detail & Related papers  (2025-07-30T15:21:22Z)
• NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models [14.630626774362606]
  Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content.<n>We propose a novel approach to induce disalignment by identifying and modifying the neurons responsible for safety constraints.
  arXiv  Detail & Related papers  (2025-04-29T05:49:35Z)
• Adaptive Soft Error Protection for Neural Network Processing [6.7356731848370295]
  Mitigating soft errors in neural networks (NNs) often incurs significant computational overhead.<n>Traditional methods mainly explored static vulnerability variations across NN components.<n>We propose a lightweight graph neural network (GNN) model capable of capturing input- and component-specific vulnerability to soft errors.
  arXiv  Detail & Related papers  (2024-07-29T02:54:52Z)
• Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons [57.07507194465299]
  Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment.<n>We focus on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors.<n>We propose inference-time activation contrasting to locate these neurons and dynamic activation patching to evaluate their causal effects on model safety.
  arXiv  Detail & Related papers  (2024-06-20T09:35:22Z)
• Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications [69.13807233595455]
  Large language models (LLMs) show inherent brittleness in their safety mechanisms. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted.
  arXiv  Detail & Related papers  (2024-02-07T18:34:38Z)
• Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach [49.1574468325115]
  Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. We propose a novel approach to DNN regularization by framing the training process as a constrained optimization problem. We employ the Augmented Lagrangian (SAL) method to achieve a more flexible and efficient regularization mechanism.
  arXiv  Detail & Related papers  (2023-10-25T13:55:35Z)
• Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems [59.57462129637796]
  This paper presents a backward reachability approach for safety verification of closed-loop systems with neural networks (NNs) The presence of NNs in the feedback loop presents a unique set of problems due to the nonlinearities in their activation functions and because NN models are generally not invertible. We present frameworks for calculating BP over-approximations for both linear and nonlinear systems with control policies represented by feedforward NNs.
  arXiv  Detail & Related papers  (2022-09-28T13:17:28Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning [0.0]
  We propose an automated verification pipeline capable of synthesizing high-quality safety shields. Our key insight involves separating safety verification from neural controller, using pre-computed verified safety shields to constrain neural controller training. Experimental results over a range of realistic high-dimensional deep RL benchmarks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2021-04-20T19:30:29Z)
• Enforcing robust control guarantees within neural network policies [76.00287474159973]
  We propose a generic nonlinear control policy class, parameterized by neural networks, that enforces the same provable robustness criteria as robust control. We demonstrate the power of this approach on several domains, improving in average-case performance over existing robust control methods and in worst-case stability over (non-robust) deep RL methods.
  arXiv  Detail & Related papers  (2020-11-16T17:14:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.