ARES: Locally Adaptive Reconstruction-based Anomaly Scoring

. How can we detect anomalies: that is, samples that significantly differ from a given set of high-dimensional data, such as images or sensor data? This is a practical problem with numerous applications and is also relevant to the goal of making learning algorithms more robust to unexpected inputs. Autoencoders are a popular approach, partly due to their simplicity and their ability to perform dimension reduction. However, the anomaly scoring function is not adaptive to the natural variation in reconstruction error across the range of normal samples, which hinders their ability to detect real anomalies. In this paper, we empirically demonstrate the importance of local adaptivity for anomaly scoring in experiments with real data. We then propose our novel Adaptive Reconstruction Error-based Scoring approach, which adapts its scoring based on the local behaviour of reconstruction error over the latent space. We show that this improves anomaly detection performance over relevant baselines in a wide variety of benchmark datasets.

[1]  Bryan Hooi,et al.  CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias , 2022, IJCAI.

[2]  Wee Siong Ng,et al.  LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks , 2021, AAAI.

[3]  Wee Siong Ng,et al.  Robustness of Autoencoders for Anomaly Detection Under Adversarial Impact , 2020, IJCAI.

[4]  Andrew Gordon Wilson,et al.  Why Normalizing Flows Fail to Detect Out-of-Distribution Data , 2020, NeurIPS.

[5]  Yongsub Lim,et al.  RaPP: Novelty Detection with Reconstruction along Projection Pathway , 2020, ICLR.

[6]  Yedid Hoshen,et al.  Deep Nearest Neighbor Anomaly Detection , 2020, ArXiv.

[7]  Simone Calderara,et al.  Latent Space Autoregression for Novelty Detection , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Keun Ho Ryu,et al.  Unsupervised Novelty Detection Using Deep Autoencoders with Density Based Clustering , 2018, Applied Sciences.

[9]  Alexander Binder,et al.  Deep One-Class Classification , 2018, ICML.

[10]  Toby P. Breckon,et al.  GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training , 2018, ACCV.

[11]  Bo Zong,et al.  Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection , 2018, ICLR.

[12]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[13]  Alexandre Termier,et al.  Anomaly Detection in Streams with Extreme Value Theory , 2017, KDD.

[14]  Iain Murray,et al.  Masked Autoregressive Flow for Density Estimation , 2017, NIPS.

[15]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[16]  Charu C. Aggarwal,et al.  Outlier Detection with Autoencoder Ensembles , 2017, SDM.

[17]  Yu Cheng,et al.  Deep Structured Energy Based Models for Anomaly Detection , 2016, ICML.

[18]  Chongzhao Han,et al.  A novel approach for trajectory feature representation and anomalous trajectory detection , 2015, 2015 18th International Conference on Information Fusion (Fusion).

[19]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[20]  Sungzoon Cho,et al.  Variational Autoencoder based Anomaly Detection using Reconstruction Probability , 2015 .

[21]  Takehisa Yairi,et al.  Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction , 2014, MLSDA'14.

[22]  Arthur Zimek,et al.  Subsampling for efficient and effective unsupervised outlier detection ensembles , 2013, KDD.

[23]  Fei Tony Liu,et al.  Isolation-Based Anomaly Detection , 2012, TKDD.

[24]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[25]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[26]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[27]  M. Shyu,et al.  A Novel Anomaly Detection Scheme Based on Principal Component Classifier , 2003 .

[28]  Thomas S. Huang,et al.  One-class SVM for learning in image retrieval , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[29]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[30]  Jonathan Goldstein,et al.  When Is ''Nearest Neighbor'' Meaningful? , 1999, ICDT.