No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks

• URL: http://arxiv.org/abs/2608.01414v1
• Date: Sun, 02 Aug 2026 17:49:07 GMT
• Title: No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks
• Abstract summary: We propose distributed safety alignment, which encodes safety capabilities across multiple computational neurons.<n>We show that DSA substantially improves against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.
• Score: 61.07406641465909
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and manipulate safety-related neurons. Existing alignment methods often investigate the safety behavior on a small number of neurons, creating fragile single point of failure with limited redundancy. To address this issue, we propose distributed safety alignment (DSA), which redundantly encodes safety capabilities across multiple computational neurons, ensuring that the model maintains its safety baseline even when critical safety neurons are disrupted. Specifically, we localize the intervention to the inputs of the down-projection layers in language-side feed-forward networks and treat each feature coordinate as the activation of an individual neuron. DSA then combines neuron activations with loss gradients to compute a direction-aware first-order Taylor score that globally identifies the neurons that contribute most to the current refusal behavior of the model. Finally, targeted disruption via deterministic masking and stochastic dropout is coupled, forcing the model to abandon narrow safety neurons and redundantly encode safety behavior across multiple compensatory neurons. Extensive experiments show that DSA substantially improves robustness against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.

Related papers

• NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution [9.458292549037155]
  Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks.<n>Jailbreak attacks bypass safety mechanisms through crafted prompts, while neuron-level attacks directly prune safety-critical neurons post-deployment.<n>We present NeuronGuard, a fine-tuning-stage defense that simultaneously hardens LLMs against both attack classes by redistributing safety signals across a broader set of neurons.
  arXiv  Detail & Related papers  (2026-08-25T01:36:54Z)
• Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons [8.627671856044527]
  We present ours, a training-free defense that identifies safety-specific neurons through per-neuron hypothesis tests.<n>Experiments show that ours reduces the average attack success rate to at most 2.0% while incurring a utility drop of only 0.5% to 5.3% on MT-Bench.
  arXiv  Detail & Related papers  (2026-08-14T15:33:11Z)
• SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs [69.51621286001262]
  We introduce SafeNexus, a cross-modal safety alignment framework that adopts a dedicated neuron-level intervention strategy.<n>We identify modality-bound safety neurons (BS-Neurons), and validate their role in regulating safety behavior within each modality.<n>We propose two safety alignment strategies: activation-level safety amplifier and safety neuron calibrator.
  arXiv  Detail & Related papers  (2026-07-31T02:45:56Z)
• Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance [64.18179414483966]
  In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks.<n>We propose Precise Shield, a two-stage framework that first identifies safety neurons by contrasting activation patterns between harmful and benign inputs.<n>This strategy substantially improves safety while preserving multilingual and multimodal generalization.
  arXiv  Detail & Related papers  (2026-04-10T02:42:52Z)
• 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)
• Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks [22.059668583508365]
  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)
• 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)
• 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)
• Improving Adversarial Transferability via Neuron Attribution-Based Attacks [35.02147088207232]
  We propose the Neuron-based Attack (NAA), which conducts feature-level attacks with more accurate neuron importance estimations. We derive an approximation scheme of neuron attribution to tremendously reduce the overhead. Experiments confirm the superiority of our approach to the state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2022-03-31T13:47:30Z)
• Few-shot Backdoor Defense Using Shapley Estimation [123.56934991060788]
  We develop a new approach called Shapley Pruning to mitigate backdoor attacks on deep neural networks. ShapPruning identifies the few infected neurons (under 1% of all neurons) and manages to protect the model's structure and accuracy. Experiments demonstrate the effectiveness and robustness of our method against various attacks and tasks.
  arXiv  Detail & Related papers  (2021-12-30T02:27:03Z)

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.