Detecting unusual input to neural networks

• URL: http://arxiv.org/abs/2006.08278v1
• Date: Mon, 15 Jun 2020 10:48:43 GMT
• Title: Detecting unusual input to neural networks
• Authors: J\"org Martin, Clemens Elster
• Abstract summary: We study a method that judges the unusualness of an input by evaluating its informative content compared to the learned parameters. This technique can be used to judge whether a network is suitable for processing a certain input and to raise a red flag that unexpected behavior might lie ahead.
• Score: 0.48733623015338234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating a neural network on an input that differs markedly from the training data might cause erratic and flawed predictions. We study a method that judges the unusualness of an input by evaluating its informative content compared to the learned parameters. This technique can be used to judge whether a network is suitable for processing a certain input and to raise a red flag that unexpected behavior might lie ahead. We compare our approach to various methods for uncertainty evaluation from the literature for various datasets and scenarios. Specifically, we introduce a simple, effective method that allows to directly compare the output of such metrics for single input points even if these metrics live on different scales.

Related papers

• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method [108.56493934296687]
  We introduce a divergence-based calibration method, inspired by the divergence-from-randomness concept, to calibrate token probabilities for pretraining data detection. We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
  arXiv  Detail & Related papers  (2024-09-23T07:55:35Z)
• A Rate-Distortion View of Uncertainty Quantification [36.85921945174863]
  In supervised learning, understanding an input's proximity to the training data can help a model decide whether it has sufficient evidence for reaching a reliable prediction. We introduce Distance Aware Bottleneck (DAB), a new method for enriching deep neural networks with this property.
  arXiv  Detail & Related papers  (2024-06-16T01:33:22Z)
• QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input [17.017127559393398]
  We propose a differentiable soft quantizer, which better simulates the gradient of the round function during backpropagation. This enables the network to learn from subtle input perturbations. We further refine the training strategy to ensure convergence while simulating quantization errors.
  arXiv  Detail & Related papers  (2024-05-22T17:34:18Z)
• 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)
• Probing the Purview of Neural Networks via Gradient Analysis [13.800680101300756]
  We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. To probe the purview of a network, we utilize gradients to measure the amount of change required for the model to characterize the given inputs more accurately. We demonstrate that our gradient-based approach can effectively differentiate inputs that cannot be accurately represented with learned features.
  arXiv  Detail & Related papers  (2023-04-06T03:02:05Z)
• Automatic Change-Point Detection in Time Series via Deep Learning [8.43086628139493]
  We show how to automatically generate new offline detection methods based on training a neural network. We present theory that quantifies the error rate for such an approach, and how it depends on the amount of training data. Our method also shows strong results in detecting and localising changes in activity based on accelerometer data.
  arXiv  Detail & Related papers  (2022-11-07T20:59:14Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else? [93.91375268580806]
  Both politics and pandemics have recently provided ample motivation for the development of machine learning-enabled disinformation (a.k.a. fake news) detection algorithms. Existing literature has focused primarily on the fully-automated case, but the resulting techniques cannot reliably detect disinformation on the varied topics, sources, and time scales required for military applications. By leveraging an already-available analyst as a human-in-the-loop, canonical machine learning techniques of sentiment analysis, aspect-based sentiment analysis, and stance detection become plausible methods to use for a partially-automated disinformation detection system.
  arXiv  Detail & Related papers  (2021-11-09T13:30:34Z)
• Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information [53.28701922632817]
  We propose a method to identify features with predictive information in the input domain. The core idea of our method is leveraging a bottleneck on the input that only lets input features associated with predictive latent features pass through.
  arXiv  Detail & Related papers  (2021-10-04T14:13:42Z)
• Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning [0.0]
  A novel probabilistic neural network is presented for the task of joint depth and uncertainty estimation from epipolar rectified stereo image pairs. The network learns a probability distribution from which parameters are sampled for every prediction. The quality of the estimated depth and uncertainty information is assessed in an extensive evaluation on three different datasets.
  arXiv  Detail & Related papers  (2020-02-10T11:27:52Z)

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.