Fuzzing the brain: Automated stress testing for the safety of ML-driven neurostimulation

• URL: http://arxiv.org/abs/2512.05383v1
• Date: Fri, 05 Dec 2025 02:43:22 GMT
• Title: Fuzzing the brain: Automated stress testing for the safety of ML-driven neurostimulation
• Authors: Mara Downing, Matthew Peng, Jacob Granley, Michael Beyeler, Tevfik Bultan,
• Abstract summary: Machine learning models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses.<n>We propose a systematic, quantitative approach to detect and characterize unsafe stimulation patterns in ML-driven neurostimulation systems.
• Score: 6.763690463901025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Objective: Machine learning (ML) models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses. While these models promise precise and personalized control, they also introduce new safety risks when model outputs are delivered directly to neural tissue. We propose a systematic, quantitative approach to detect and characterize unsafe stimulation patterns in ML-driven neurostimulation systems. Approach: We adapt an automated software testing technique known as coverage-guided fuzzing to the domain of neural stimulation. Here, fuzzing performs stress testing by perturbing model inputs and tracking whether resulting stimulation violates biophysical limits on charge density, instantaneous current, or electrode co-activation. The framework treats encoders as black boxes and steers exploration with coverage metrics that quantify how broadly test cases span the space of possible outputs and violation types. Main results: Applied to deep stimulus encoders for the retina and cortex, the method systematically reveals diverse stimulation regimes that exceed established safety limits. Two violation-output coverage metrics identify the highest number and diversity of unsafe outputs, enabling interpretable comparisons across architectures and training strategies. Significance: Violation-focused fuzzing reframes safety assessment as an empirical, reproducible process. By transforming safety from a training heuristic into a measurable property of the deployed model, it establishes a foundation for evidence-based benchmarking, regulatory readiness, and ethical assurance in next-generation neural interfaces.

Related papers

• AI-Powered Machine Learning Approaches for Fault Diagnosis in Industrial Pumps [0.0]
  This study presents a practical approach for early fault detection in industrial pump systems using real-world sensor data.<n>The framework is scalable, interpretable, and suitable for real-time industrial deployment.
  arXiv  Detail & Related papers  (2025-08-21T13:33:09Z)
• An Adversarial-Driven Experimental Study on Deep Learning for RF Fingerprinting [6.145167956956878]
  Radio frequency (RF) fingerprinting has emerged as a promising physical-layer device identification mechanism.<n>Deep learning (DL) methods have demonstrated state-of-the-art performance in this domain.<n>We show that training DL models on raw received signals causes the models to entangle RF fingerprints with environmental and signal-pattern features.
  arXiv  Detail & Related papers  (2025-07-18T17:42:20Z)
• Certified Neural Approximations of Nonlinear Dynamics [51.01318247729693]
  In safety-critical contexts, the use of neural approximations requires formal bounds on their closeness to the underlying system.<n>We propose a novel, adaptive, and parallelizable verification method based on certified first-order models.
  arXiv  Detail & Related papers  (2025-05-21T13:22:20Z)
• 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)
• Neural Abstractions [72.42530499990028]
  We present a novel method for the safety verification of nonlinear dynamical models that uses neural networks to represent abstractions of their dynamics. We demonstrate that our approach performs comparably to the mature tool Flow* on existing benchmark nonlinear models.
  arXiv  Detail & Related papers  (2023-01-27T12:38:09Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Neuro-BERT: Rethinking Masked Autoencoding for Self-supervised Neurological Pretraining [24.641328814546842]
  We present Neuro-BERT, a self-supervised pre-training framework of neurological signals based on masked autoencoding in the Fourier domain. We propose a novel pre-training task dubbed Fourier Inversion Prediction (FIP), which randomly masks out a portion of the input signal and then predicts the missing information. By evaluating our method on several benchmark datasets, we show that Neuro-BERT improves downstream neurological-related tasks by a large margin.
  arXiv  Detail & Related papers  (2022-04-20T16:48:18Z)
• Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems [2.088376060651494]
  This paper presents preliminary results on evaluating the robustness of ML-based anomaly detection methods in safety-critical CPS. We test the hypothesis of whether integrating the domain knowledge (e.g., on unsafe system behavior) with the ML models can improve the robustness of anomaly detection without sacrificing accuracy and transparency.
  arXiv  Detail & Related papers  (2022-04-20T02:02:56Z)
• DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals [62.997667081978825]
  We develop a novel statistical point process model-called driven temporal point processes (DriPP) We derive a fast and principled expectation-maximization (EM) algorithm to estimate the parameters of this model. Results on standard MEG datasets demonstrate that our methodology reveals event-related neural responses.
  arXiv  Detail & Related papers  (2021-12-08T13:07:21Z)
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis [71.57324258813674]
  This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model against different unsafe inputs. Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs.
  arXiv  Detail & Related papers  (2021-01-28T16:38:26Z)

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.