Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks

• URL: http://arxiv.org/abs/2508.09190v3
• Date: Sun, 24 Aug 2025 09:31:13 GMT
• Title: Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks
• Authors: Bing Han, Feifei Zhao, Dongcheng Zhao, Guobin Shen, Ping Wu, Yu Shi, Yi Zeng,
• Abstract summary: 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.
• Score: 22.059668583508365
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Fine-tuning as service injects domain-specific knowledge into large language models (LLMs), while challenging the original alignment mechanisms and introducing safety risks. A series of defense strategies have been proposed for the alignment, fine-tuning, and post-fine-tuning phases, where most post-fine-tuning defenses rely on coarse-grained safety layer mapping. These methods lack a comprehensive consideration of both safety layers and fine-grained neurons, limiting their ability to efficiently balance safety and utility. To address this, we propose the Fine-Grained Safety Neurons (FGSN) with Training-Free Continual Projection method to reduce the fine-tuning safety risks. FGSN inherently integrates the multi-scale interactions between safety layers and neurons, localizing sparser and more precise fine-grained safety neurons while minimizing interference with downstream task neurons. We then project the safety neuron parameters onto safety directions, improving model safety while aligning more closely with human preferences. Extensive experiments across multiple fine-tuned LLM models demonstrate that our method significantly reduce harmfulness scores and attack success rates with minimal parameter modifications, while preserving the model's utility. Furthermore, by introducing a task-specific, multi-dimensional heterogeneous safety neuron cluster optimization mechanism, we achieve continual defense and generalization capability against unforeseen emerging safety concerns.

Related papers

• NeST: Neuron Selective Tuning for LLM Safety [12.78786094112]
  Safety alignment is essential for the responsible deployment of large language models (LLMs)<n>We present NeST, a lightweight, structure-aware safety alignment framework that strengthens refusal behavior by selectively adapting a small subset of safety-relevant neurons.<n>We benchmark NeST against three dominant baselines: full fine-tuning, LoRA-based fine-tuning, and circuit breakers across 10 open-weight LLMs.
  arXiv  Detail & Related papers  (2026-02-18T20:01:01Z)
• 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)
• LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion [16.434293020863592]
  The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities.<n>We introduce LSSF, a novel safety re-alignment framework with underlineLow-Rank underlineSafety underlineSubspace underlineFusion.<n>Our proposed method exploits the low-rank characteristics of safety information in LLMs by constructing a low-rank projection matrix.
  arXiv  Detail & Related papers  (2026-01-19T03:59:12Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• 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)
• NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs [19.133502330591092]
  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.
  arXiv  Detail & Related papers  (2025-08-13T04:05:28Z)
• LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning [61.594212398272184]
  Low-Rank Extrapolation (LoX) improves robustness against benign and malicious fine-tuning attacks.<n>LoX leads to 11% to 54% absolute reductions in attack success rates.
  arXiv  Detail & Related papers  (2025-06-18T16:30:02Z)
• SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety [57.14003339251827]
  We introduce a new algorithm called SafeDPO, which is designed to directly optimize the safety alignment objective in a single stage of policy learning.<n>As a result, it eliminates the need to fit separate reward and cost models or to sample from the language model during fine-tuning.<n>We demonstrate that SafeDPO achieves competitive performance compared to state-of-the-art safety alignment algorithms.
  arXiv  Detail & Related papers  (2025-05-26T14:50:01Z)
• Shape it Up! Restoring LLM Safety during Finetuning [66.46166656543761]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• 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)
• NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning [37.024666077902225]
  A handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken model.<n>Existing methods to counteract fine-tuning attacks typically require substantial computational resources.<n>We propose textbfNeuron-textbfLevel textbfSafety textbfRealignment.
  arXiv  Detail & Related papers  (2024-12-17T02:59:04Z)
• Superficial Safety Alignment Hypothesis [8.297367440457508]
  We propose the Superficial Safety Alignment Hypothesis (SSAH), which posits that safety alignment should teach an otherwise unsafe model to choose the correct reasoning direction. We identify four types of attribute-critical components in safety-aligned large language models (LLMs) Our findings show that freezing certain safety-critical components 7.5% during fine-tuning allows the model to retain its safety attributes while adapting to new tasks.
  arXiv  Detail & Related papers  (2024-10-07T19:53:35Z)
• 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)
• Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching [74.62818936088065]
  textscSafePatching is a novel framework for comprehensive PSA.<n>textscSafePatching achieves a more comprehensive PSA than baseline methods.<n>textscSafePatching demonstrates its superiority in continual PSA scenarios.
  arXiv  Detail & Related papers  (2024-05-22T16:51:07Z)

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.