Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks

• URL: http://arxiv.org/abs/2508.21715v1
• Date: Fri, 29 Aug 2025 15:33:45 GMT
• Title: Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
• Authors: Amirhossein Nazeri, Wael Hafez,
• Abstract summary: We show that adversarial perturbations create immediate, detectable entropy signatures in CNN activations.<n>We demonstrate that adversarial inputs consistently shift activation entropy by 7% in early convolutional layers.<n>This work establishes that CNN reliability can be assessed through activation entropy alone, enabling practical deployment of self-diagnostic vision systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Convolutional Neural Networks (CNNs) have become the foundation of modern computer vision, achieving unprecedented accuracy across diverse image recognition tasks. While these networks excel on in-distribution data, they remain vulnerable to adversarial perturbations imperceptible input modifications that cause misclassification with high confidence. However, existing detection methods either require expensive retraining, modify network architecture, or degrade performance on clean inputs. Here we show that adversarial perturbations create immediate, detectable entropy signatures in CNN activations that can be monitored without any model modification. Using parallel entropy monitoring on VGG-16, we demonstrate that adversarial inputs consistently shift activation entropy by 7% in early convolutional layers, enabling 90% detection accuracy with false positives and false negative rates below 20%. The complete separation between clean and adversarial entropy distributions reveals that CNNs inherently encode distribution shifts in their activation patterns. This work establishes that CNN reliability can be assessed through activation entropy alone, enabling practical deployment of self-diagnostic vision systems that detect adversarial inputs in real-time without compromising original model performance.

Related papers

• Self-Supervised Learning of Graph Representations for Network Intrusion Detection [6.453778601809096]
  GraphIDS is a self-supervised intrusion detection model that unifies representation learning and anomaly detection.<n>An inductive graph neural network embeds each flow with its local topological context to capture typical network behavior.<n>A Transformer-based encoder-decoder reconstructs these embeddings, implicitly learning global co-occurrence patterns via self-attention.<n>During inference, flows with unusually high reconstruction errors are flagged as potential intrusions.
  arXiv  Detail & Related papers  (2025-09-20T11:02:50Z)
• A Temporal Convolutional Network-based Approach for Network Intrusion Detection [0.0]
  This study proposes a Temporal Convolutional Network(TCN) model featuring a residual block architecture with dilated convolutions to capture dependencies in network traffic data.<n>The proposed model achieved an accuracy of 96.72% and a loss of 0.0688, outperforming 1D CNN, CNN-LSTM, CNN-GRU, CNN-BiLSTM, and CNN-GRU-LSTM models.
  arXiv  Detail & Related papers  (2024-12-23T10:19:29Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• How adversarial attacks can disrupt seemingly stable accurate classifiers [76.95145661711514]
  Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Here, we show that this may be seen as a fundamental feature of classifiers working with high dimensional input data. We introduce a simple generic and generalisable framework for which key behaviours observed in practical systems arise with high probability.
  arXiv  Detail & Related papers  (2023-09-07T12:02:00Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Certified Invertibility in Neural Networks via Mixed-Integer Programming [16.64960701212292]
  Neural networks are known to be vulnerable to adversarial attacks. There may exist large, meaningful perturbations that do not affect the network's decision. We discuss how our findings can be useful for invertibility certification in transformations between neural networks.
  arXiv  Detail & Related papers  (2023-01-27T15:40:38Z)
• Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection [22.99930028876662]
  Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. Current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system. We propose a simple and light-weight detector, which leverages recent findings on the relation between networks' local intrinsic dimensionality (LID) and adversarial attacks.
  arXiv  Detail & Related papers  (2022-12-13T17:51:32Z)
• A Robust Backpropagation-Free Framework for Images [47.97322346441165]
  We present an error kernel driven activation alignment algorithm for image data. EKDAA accomplishes through the introduction of locally derived error transmission kernels and error maps. Results are presented for an EKDAA trained CNN that employs a non-differentiable activation function.
  arXiv  Detail & Related papers  (2022-06-03T21:14:10Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• Implementing a foveal-pit inspired filter in a Spiking Convolutional Neural Network: a preliminary study [0.0]
  We have presented a Spiking Convolutional Neural Network (SCNN) that incorporates retinal foveal-pit inspired Difference of Gaussian filters and rank-order encoding. The model is trained using a variant of the backpropagation algorithm adapted to work with spiking neurons, as implemented in the Nengo library. The network has achieved up to 90% accuracy, where loss is calculated using the cross-entropy function.
  arXiv  Detail & Related papers  (2021-05-29T15:28:30Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)

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.