Certifiably Adversarially Robust Detection of Out-of-Distribution Data

• URL: http://arxiv.org/abs/2007.08473v3
• Date: Wed, 10 Mar 2021 15:55:00 GMT
• Title: Certifiably Adversarially Robust Detection of Out-of-Distribution Data
• Authors: Julian Bitterwolf, Alexander Meinke and Matthias Hein
• Abstract summary: We aim for certifiable worst case guarantees for OOD detection by enforcing low confidence at the OOD point. We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible.
• Score: 111.67388500330273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks are known to be overconfident when applied to out-of-distribution (OOD) inputs which clearly do not belong to any class. This is a problem in safety-critical applications since a reliable assessment of the uncertainty of a classifier is a key property, allowing the system to trigger human intervention or to transfer into a safe state. In this paper, we aim for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an $l_\infty$-ball around it. For this purpose, we use interval bound propagation (IBP) to upper bound the maximal confidence in the $l_\infty$-ball and minimize this upper bound during training time. We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible. Moreover, in contrast to certified adversarial robustness which typically comes with significant loss in prediction performance, certified guarantees for worst case OOD detection are possible without much loss in accuracy.

Related papers

• The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection [75.65876949930258]
  Out-of-distribution (OOD) detection is essential for model trustworthiness. We show that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability.
  arXiv  Detail & Related papers  (2024-10-12T07:02:04Z)
• Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations [1.8531577178922987]
  "Overconfidence" is an intrinsic property of certain neural network architectures, leading to poor OOD detection. We measure extreme activation values in the penultimate layer of neural networks and then leverage this proxy of overconfidence to improve on several OOD detection baselines. Compared to the baselines, our method often grants substantial improvements, with double-digit increases in OOD detection.
  arXiv  Detail & Related papers  (2024-05-21T10:14:50Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training [29.4569172720654]
  We develop a simple adversarial training scheme that incorporates an attack of the uncertainty predicted by the dropout ensemble. We demonstrate this method improves OOD detection performance on standard data (i.e., not adversarially crafted), and improves the standardized partial AUC from near-random guessing performance to $geq 0.75$.
  arXiv  Detail & Related papers  (2022-09-05T14:32:19Z)
• 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)
• 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)
• Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning [17.10036674236381]
  Wrong predictions for out-of-distribution data can cause safety critical situations in machine learning systems. We propose a framework for uncertainty-based OOD classification: UBOOD. We show that UBOOD produces reliable classification results when combined with ensemble-based estimators.
  arXiv  Detail & Related papers  (2019-12-31T09:52:49Z)

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.