Fine-grained Anomaly Detection in Sequential Data via Counterfactual
Explanations
- URL: http://arxiv.org/abs/2210.04145v1
- Date: Sun, 9 Oct 2022 02:38:11 GMT
- Title: Fine-grained Anomaly Detection in Sequential Data via Counterfactual
Explanations
- Authors: He Cheng, Depeng Xu, Shuhan Yuan, Xintao Wu
- Abstract summary: We propose a novel framework called CFDet for fine-grained anomalous entry detection.
Given a sequence that is detected as anomalous, we can consider anomalous entry detection as an interpretable machine learning task.
We make use of the deep support vector data description (Deep SVDD) approach to detect anomalous sequences and propose a novel counterfactual interpretation-based approach to identify anomalous entries in the sequences.
- Score: 19.836395281552626
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Anomaly detection in sequential data has been studied for a long time because
of its potential in various applications, such as detecting abnormal system
behaviors from log data. Although many approaches can achieve good performance
on anomalous sequence detection, how to identify the anomalous entries in
sequences is still challenging due to a lack of information at the entry-level.
In this work, we propose a novel framework called CFDet for fine-grained
anomalous entry detection. CFDet leverages the idea of interpretable machine
learning. Given a sequence that is detected as anomalous, we can consider
anomalous entry detection as an interpretable machine learning task because
identifying anomalous entries in the sequence is to provide an interpretation
to the detection result. We make use of the deep support vector data
description (Deep SVDD) approach to detect anomalous sequences and propose a
novel counterfactual interpretation-based approach to identify anomalous
entries in the sequences. Experimental results on three datasets show that
CFDet can correctly detect anomalous entries.
Related papers
- Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection [49.91075101563298]
A novel framework is proposed to guide the learning of suspected anomalies from event prompts.
It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos.
Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC.
arXiv Detail & Related papers (2024-03-02T10:42:47Z) - Unraveling the "Anomaly" in Time Series Anomaly Detection: A
Self-supervised Tri-domain Solution [89.16750999704969]
Anomaly labels hinder traditional supervised models in time series anomaly detection.
Various SOTA deep learning techniques, such as self-supervised learning, have been introduced to tackle this issue.
We propose a novel self-supervised learning based Tri-domain Anomaly Detector (TriAD)
arXiv Detail & Related papers (2023-11-19T05:37:18Z) - CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection [53.83593870825628]
One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios.
Most of the existing anomaly detection methods focus on learning the normal behaviour of unlabelled time series in an unsupervised manner.
We introduce a novel end-to-end self-supervised ContrAstive Representation Learning approach for time series anomaly detection.
arXiv Detail & Related papers (2023-08-18T04:45:56Z) - PULL: Reactive Log Anomaly Detection Based On Iterative PU Learning [58.85063149619348]
We propose PULL, an iterative log analysis method for reactive anomaly detection based on estimated failure time windows.
Our evaluation shows that PULL consistently outperforms ten benchmark baselines across three different datasets.
arXiv Detail & Related papers (2023-01-25T16:34:43Z) - Are we certain it's anomalous? [57.729669157989235]
Anomaly detection in time series is a complex task since anomalies are rare due to highly non-linear temporal correlations.
Here we propose the novel use of Hyperbolic uncertainty for Anomaly Detection (HypAD)
HypAD learns self-supervisedly to reconstruct the input signal.
arXiv Detail & Related papers (2022-11-16T21:31:39Z) - Series2Graph: Graph-based Subsequence Anomaly Detection for Time Series [22.630676187747696]
Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains.
In this work, we propose an unsupervised method suitable for domain subsequence anomaly detection.
Our method, Series2Graph, is based on a graph representation of a novel low-dimensional agnosticity embedding of subsequences.
arXiv Detail & Related papers (2022-07-25T13:55:43Z) - Anomaly Rule Detection in Sequence Data [2.3757190901941736]
We present a new anomaly detection framework called DUOS that enables Discovery of Utility-aware Outlier Sequential rules from a set of sequences.
In this work, we incorporate both the anomalousness and utility of a group, and then introduce the concept of utility-aware outlier rule (UOSR)
arXiv Detail & Related papers (2021-11-29T23:52:31Z) - A Taxonomy of Anomalies in Log Data [0.09558392439655014]
A common taxonomy for anomalies already exists, but it has not yet been applied specifically to log data.
We present a taxonomy for different kinds of log data anomalies and introduce a method for analyzing such anomalies in labeled datasets.
Our results show, that the most common anomaly type is also the easiest to predict.
arXiv Detail & Related papers (2021-11-26T12:23:06Z) - DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly
Detection [9.19194451963411]
Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data.
We propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation.
arXiv Detail & Related papers (2021-06-09T21:57:41Z) - Multi-Scale One-Class Recurrent Neural Networks for Discrete Event
Sequence Anomaly Detection [63.825781848587376]
We propose OC4Seq, a one-class recurrent neural network for detecting anomalies in discrete event sequences.
Specifically, OC4Seq embeds the discrete event sequences into latent spaces, where anomalies can be easily detected.
arXiv Detail & Related papers (2020-08-31T04:48:22Z) - Sequential Adversarial Anomaly Detection for One-Class Event Data [18.577418448786634]
We consider the sequential anomaly detection problem in the one-class setting when only the anomalous sequences are available.
We propose an adversarial sequential detector by solving a minimax problem to find an optimal detector against the worst-case sequences from a generator.
arXiv Detail & Related papers (2019-10-21T06:12:47Z)
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.