Towards Rigorous Design of OoD Detectors

• URL: http://arxiv.org/abs/2306.08447v1
• Date: Wed, 14 Jun 2023 11:38:36 GMT
• Title: Towards Rigorous Design of OoD Detectors
• Authors: Chih-Hong Cheng, Changshun Wu, Harald Ruess, Saddek Bensalem
• Abstract summary: Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. Current performance-oriented OoD detection techniques geared towards matching metrics are not sufficient for establishing safety claims. What is missing is a rigorous design approach for developing, verifying, and validating OoD detectors.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. We are arguing, however, that current performance-oriented OoD detection techniques geared towards matching metrics such as expected calibration error, are not sufficient for establishing safety claims. What is missing is a rigorous design approach for developing, verifying, and validating OoD detectors. These design principles need to be aligned with the intended functionality and the operational domain. Here, we formulate some of the key technical challenges, together with a possible way forward, for developing a rigorous and safety-related design methodology for OoD detectors.

Related papers

• Convolutional Neural Network Design and Evaluation for Real-Time Multivariate Time Series Fault Detection in Spacecraft Attitude Sensors [41.94295877935867]
  This paper presents a novel approach to detecting stuck values within the Accelerometer and Inertial Measurement Unit of a drone-like spacecraft. A multi-channel Convolutional Neural Network (CNN) is used to perform multi-target classification and independently detect faults in the sensors. An integration methodology is proposed to enable the network to effectively detect anomalies and trigger recovery actions at the system level.
  arXiv  Detail & Related papers  (2024-10-11T09:36:38Z)
• A Flow-based Credibility Metric for Safety-critical Pedestrian Detection [16.663568842153065]
  Safety is of utmost importance for perception in automated driving (AD) Standard evaluation schemes utilize safety-agnostic metrics to argue sufficient detection performance. This paper introduces a novel credibility metric, called c-flow, for pedestrian bounding boxes.
  arXiv  Detail & Related papers  (2024-02-12T13:30:34Z)
• AI-Based Energy Transportation Safety: Pipeline Radial Threat Estimation Using Intelligent Sensing System [52.93806509364342]
  This paper proposes a radial threat estimation method for energy pipelines based on distributed optical fiber sensing technology. We introduce a continuous multi-view and multi-domain feature fusion methodology to extract comprehensive signal features. We incorporate the concept of transfer learning through a pre-trained model, enhancing both recognition accuracy and training efficiency.
  arXiv  Detail & Related papers  (2023-12-18T12:37:35Z)
• Cal-DETR: Calibrated Detection Transformer [67.75361289429013]
  We propose a mechanism for calibrated detection transformers (Cal-DETR), particularly for Deformable-DETR, UP-DETR and DINO. We develop an uncertainty-guided logit modulation mechanism that leverages the uncertainty to modulate the class logits. Results corroborate the effectiveness of Cal-DETR against the competing train-time methods in calibrating both in-domain and out-domain detections.
  arXiv  Detail & Related papers  (2023-11-06T22:13:10Z)
• Runtime Monitoring DNN-Based Perception [5.518665721709856]
  This tutorial aims to provide readers with a glimpse of techniques proposed in the literature. We start with classical methods proposed in the machine learning community, then highlight a few techniques proposed by the formal methods community. We conclude by highlighting the need to rigorously design monitors, where data availability outside the operational domain plays an important role.
  arXiv  Detail & Related papers  (2023-10-06T03:57:56Z)
• Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking [57.96787187733302]
  Reversible data hiding (RDH) methods offer a potential solution, but existing approaches suffer from weaknesses in terms of usability, capacity, and fidelity. We propose a novel RDH-based static DNN watermarking scheme using quantization index modulation (QIM) Our scheme incorporates a novel approach based on a one-dimensional quantizer for watermark embedding.
  arXiv  Detail & Related papers  (2023-05-29T04:39:17Z)
• Continual Detection Transformer for Incremental Object Detection [154.8345288298059]
  Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exemplar replay (ER) We propose a new method for transformer-based IOD which enables effective usage of KD and ER in this context.
  arXiv  Detail & Related papers  (2023-04-06T14:38:40Z)
• Countering detector manipulation attacks in quantum communication through detector self-testing [0.0]
  A vulnerability in single-photon detectors to blinding attacks has been one of the biggest concerns. We present a countermeasure based on self-testing of detectors to confirm their intended operation.
  arXiv  Detail & Related papers  (2022-04-13T03:36:54Z)
• Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification [81.32981236437395]
  We present a semi-formal verification approach for decision-making tasks based on interval analysis. Our method obtains comparable results over standard benchmarks with respect to formal verifiers. Our approach allows to efficiently evaluate safety properties for decision-making models in practical applications.
  arXiv  Detail & Related papers  (2020-10-19T11:18:06Z)
• NADS: Neural Architecture Distribution Search for Uncertainty Awareness [79.18710225716791]
  Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. Existing OoD detection approaches are prone to errors and even sometimes assign higher likelihoods to OoD samples. We propose Neural Architecture Distribution Search (NADS) to identify common building blocks among all uncertainty-aware architectures.
  arXiv  Detail & Related papers  (2020-06-11T17:39:07Z)

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.