Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks

• URL: http://arxiv.org/abs/2403.08652v1
• Date: Wed, 13 Mar 2024 16:06:26 GMT
• Title: Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks
• Authors: Paul Ardis, Arjuna Flenner
• Abstract summary: We propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from Deep Neural Networks. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly detection and out-of-distribution detection tasks. We validate our approach on the CIFAR-10 dataset, and show that it can significantly improve the interpretability and reliability of DNNs.

Related papers

• Uncertainty in Graph Neural Networks: A Survey [50.63474656037679]
  Graph Neural Networks (GNNs) have been extensively used in various real-world applications. However, the predictive uncertainty of GNNs stemming from diverse sources can lead to unstable and erroneous predictions. This survey aims to provide a comprehensive overview of the GNNs from the perspective of uncertainty.
  arXiv  Detail & Related papers  (2024-03-11T21:54:52Z)
• Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees [86.1362094580439]
  We introduce the AllDNN-Verification problem: given a safety property and a DNN, enumerate the set of all the regions of the property input domain which are safe. Due to the #P-hardness of the problem, we propose an efficient approximation method called epsilon-ProVe. Our approach exploits a controllable underestimation of the output reachable sets obtained via statistical prediction of tolerance limits.
  arXiv  Detail & Related papers  (2023-08-18T22:30:35Z)
• OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks [7.797299214812479]
  Occlusion is a prevalent and easily realizable semantic perturbation to deep neural networks (DNNs) It can fool a DNN into misclassifying an input image by occluding some segments, possibly resulting in severe errors. Most existing robustness verification approaches for DNNs are focused on non-semantic perturbations.
  arXiv  Detail & Related papers  (2023-01-27T18:54:00Z)
• The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks [94.63547069706459]
  #DNN-Verification problem involves counting the number of input configurations of a DNN that result in a violation of a safety property. We propose a novel approach that returns the exact count of violations. We present experimental results on a set of safety-critical benchmarks.
  arXiv  Detail & Related papers  (2023-01-17T18:32:01Z)
• Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training [14.787056022080625]
  This paper presents a novel abstraction-based approach to bypass the crux of over-approximating DNNs in reachability analysis. We extend conventional DNNs by inserting an additional abstraction layer, which abstracts a real number to an interval for training. We devise the first black-box reachability analysis approach for DNN-controlled systems, where trained DNNs are only queried as black-box oracles for the actions on abstract states.
  arXiv  Detail & Related papers  (2022-11-21T00:11:50Z)
• Verifying And Interpreting Neural Networks using Finite Automata [2.048226951354646]
  We propose an automata-theoric approach to tackling problems arising in DNN analysis. We show that the input-output behaviour of a DNN can be captured precisely by a weak B"uchi automaton.
  arXiv  Detail & Related papers  (2022-11-02T10:35:05Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Towards Fully Interpretable Deep Neural Networks: Are We There Yet? [17.88784870849724]
  Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. This paper provides a review of existing methods to develop DNNs with intrinsic interpretability.
  arXiv  Detail & Related papers  (2021-06-24T16:37:34Z)
• Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey [77.99182201815763]
  Deep Neural Networks (DNNs) achieve state-of-the-art results in many different problem settings. DNNs are often treated as black box systems, which complicates their evaluation and validation. One promising field, inspired by the success of convolutional neural networks (CNNs) in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations.
  arXiv  Detail & Related papers  (2020-06-30T14:56:05Z)
• Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions [121.10450359856242]
  Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data. Existing approaches for uncertainty quantification in RNNs are based predominantly on Bayesian methods. We develop a frequentist alternative that: (a) does not interfere with model training or compromise its accuracy, (b) applies to any RNN architecture, and (c) provides theoretical coverage guarantees on the estimated uncertainty intervals.
  arXiv  Detail & Related papers  (2020-06-20T22:45:32Z)
• Interval Neural Networks: Uncertainty Scores [11.74565957328407]
  We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic. In numerical experiments on an image reconstruction task, we demonstrate the practical utility of INNs as a proxy for the prediction error.
  arXiv  Detail & Related papers  (2020-03-25T18:03:51Z)

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.