Data-Driven Assessment of Deep Neural Networks with Random Input Uncertainty

• URL: http://arxiv.org/abs/2010.01171v1
• Date: Fri, 2 Oct 2020 19:13:35 GMT
• Title: Data-Driven Assessment of Deep Neural Networks with Random Input Uncertainty
• Authors: Brendon G. Anderson, Somayeh Sojoudi
• Abstract summary: We develop a data-driven optimization-based method capable of simultaneously certifying the safety of network outputs and localizing them. We experimentally demonstrate the efficacy and tractability of the method on a deep ReLU network.
• Score: 14.191310794366075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When using deep neural networks to operate safety-critical systems, assessing the sensitivity of the network outputs when subject to uncertain inputs is of paramount importance. Such assessment is commonly done using reachability analysis or robustness certification. However, certification techniques typically ignore localization information, while reachable set methods can fail to issue robustness guarantees. Furthermore, many advanced methods are either computationally intractable in practice or restricted to very specific models. In this paper, we develop a data-driven optimization-based method capable of simultaneously certifying the safety of network outputs and localizing them. The proposed method provides a unified assessment framework, as it subsumes state-of-the-art reachability analysis and robustness certification. The method applies to deep neural networks of all sizes and structures, and to random input uncertainty with a general distribution. We develop sufficient conditions for the convexity of the underlying optimization, and for the number of data samples to certify and localize the outputs with overwhelming probability. We experimentally demonstrate the efficacy and tractability of the method on a deep ReLU network.

Related papers

• Certifying Global Robustness for Deep Neural Networks [3.8556106468003613]
  A globally deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks.
  arXiv  Detail & Related papers  (2024-05-31T00:46:04Z)
• Distributionally Robust Statistical Verification with Imprecise Neural Networks [4.094049541486327]
  A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. This paper proposes a novel approach based on a combination of active learning, uncertainty quantification, and neural network verification.
  arXiv  Detail & Related papers  (2023-08-28T18:06:24Z)
• 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)
• Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space [0.0]
  We develop an algorithm that exploits the latent-space representation of data points fed into the network to assess the accuracy of their prediction. We show on a synthetic dataset that commonly used methods are mostly overconfident. In contrast, our method can detect such out-of-distribution data points as inaccurately predicted, thus aiding in the automatic detection of outliers.
  arXiv  Detail & Related papers  (2023-05-18T09:52:06Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks [58.195261590442406]
  We study the problem of training and certifying adversarially robust quantized neural networks (QNNs) Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization. We present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs.
  arXiv  Detail & Related papers  (2022-11-29T13:32:38Z)
• Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
  Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier. In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
  arXiv  Detail & Related papers  (2021-06-08T11:40:49Z)
• 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)
• Out-of-Distribution Detection for Automotive Perception [58.34808836642603]
  Neural networks (NNs) are widely used for object classification in autonomous driving. NNs can fail on input data not well represented by the training dataset, known as out-of-distribution (OOD) data. This paper presents a method for determining whether inputs are OOD, which does not require OOD data during training and does not increase the computational cost of inference.
  arXiv  Detail & Related papers  (2020-11-03T01:46:35Z)
• Confidence-Aware Learning for Deep Neural Networks [4.9812879456945]
  We propose a method of training deep neural networks with a novel loss function, named Correctness Ranking Loss. It regularizes class probabilities explicitly to be better confidence estimates in terms of ordinal ranking according to confidence. It has almost the same computational costs for training as conventional deep classifiers and outputs reliable predictions by a single inference.
  arXiv  Detail & Related papers  (2020-07-03T02:00:35Z)
• Scalable Quantitative Verification For Deep Neural Networks [44.570783946111334]
  We propose a test-driven verification framework for deep neural networks (DNNs) Our technique performs enough tests until soundness of a formal probabilistic property can be proven. Our work paves the way for verifying properties of distributions captured by real-world deep neural networks, with provable guarantees.
  arXiv  Detail & Related papers  (2020-02-17T09:53:50Z)

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.