Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data

• URL: http://arxiv.org/abs/2602.18674v1
• Date: Sat, 21 Feb 2026 00:55:47 GMT
• Title: Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data
• Abstract summary: We analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification.<n>For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification. For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units.

Related papers

• Robustness of neural networks to random noise perturbations of their inputs [0.0]
  We investigate the robustness of a trained neural network to the perturbation of its input values.<n>We present a robustness measure, which suggests an upper bound on the mean squared error of the network.
  arXiv  Detail & Related papers  (2026-06-30T12:36:21Z)
• Network Inversion of Binarised Neural Nets [3.5571131514746837]
  Network inversion plays a pivotal role in unraveling the black-box nature of input to output mappings in neural networks. This paper introduces a novel approach to invert a trained BNN by encoding it into a CNF formula that captures the network's structure.
  arXiv  Detail & Related papers  (2024-02-19T09:39:54Z)
• Set-Based Training for Neural Network Verification [8.97708612393722]
  Small input perturbations can significantly affect the outputs of a neural network.<n>To ensure safety of neural networks in safety-critical environments, the robustness of a neural network must be verified.<n>We present a novel set-based training procedure in which we compute the set of possible outputs.
  arXiv  Detail & Related papers  (2024-01-26T15:52:41Z)
• 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)
• Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy [52.40331776572531]
  We show that learning depth-$3$ ReLU networks under the Gaussian input distribution is hard even in the smoothed-analysis framework. Our results are under a well-studied assumption on the existence of local pseudorandom generators.
  arXiv  Detail & Related papers  (2023-02-15T02:00:26Z)
• 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)
• On the Robustness and Anomaly Detection of Sparse Neural Networks [28.832060124537843]
  We show that sparsity can make networks more robust and better anomaly detectors. We also show that structured sparsity greatly helps in reducing the complexity of expensive robustness and detection methods. We introduce a new method, SensNorm, which uses the sensitivity of weights derived from an appropriate pruning method to detect anomalous samples.
  arXiv  Detail & Related papers  (2022-07-09T09:03:52Z)
• Variational Neural Networks [88.24021148516319]
  We propose a method for uncertainty estimation in neural networks called Variational Neural Network (VNN) VNN generates parameters for the output distribution of a layer by transforming its inputs with learnable sub-layers. In uncertainty quality estimation experiments, we show that VNNs achieve better uncertainty quality than Monte Carlo Dropout or Bayes By Backpropagation methods.
  arXiv  Detail & Related papers  (2022-07-04T15:41:02Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Verifying Low-dimensional Input Neural Networks via Input Quantization [12.42030531015912]
  This paper revisits the original problem of verifying ACAS Xu networks. We propose to prepend an input quantization layer to the network. Our technique can deliver exact verification results immune to floating-point error.
  arXiv  Detail & Related papers  (2021-08-18T03:42:05Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)

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.