Perfect density models cannot guarantee anomaly detection
University of Oxford（牛津大学）；Google Research（谷歌研究院）
Charline Le Lan, Laurent Dinh
备注：
Accepted to the Special Issue "Probabilistic Methods for Deep Learning" of the Journal Entropy. 14 pages and 10 figures in main content, 4 pages of bibliography, and 2 pages in Appendix
Thanks to the tractability of their likelihood, several deep generative models show promise for seemingly straightforward but important applications like anomaly detection, uncertainty estimation, and active learning. However, the likelihood values empirically attributed to anomalies conflict with the expectations these proposed applications suggest. In this paper, we take a closer look at the behavior of distribution densities through the lens of reparametrization and show that these quantities carry less meaningful information than previously thought, beyond estimation issues or the curse of dimensionality. We conclude that the use of these likelihoods for anomaly detection relies on strong and implicit hypotheses, and highlight the necessity of explicitly formulating these assumptions for reliable anomaly detection.
Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving. Given their safety-criticality, these applications benefit from provable bounds on various errors in anomaly detection. To achieve this goal in the semi-supervised setting, we propose to provide Probably Approximately Correct (PAC) guarantees on the false negative and false positive detection rates for anomaly detection algorithms. Our method (PAC-Wrap) can wrap around virtually any existing semi-supervised and unsupervised anomaly detection method, endowing it with rigoro…
Kunumi；University of Cambridge（剑桥大学）；DeepMind；UFMG（米纳斯吉拉斯联邦大学）
Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through appropriate expert feedback. Thus, in this work we present an active learning method that can be built upon existing deep learning solutions for unsupervised anomaly detection, so that outliers can be separated from normal data effectively. We introduce a new layer that can be easily a…
We consider a setting, where the output of a linear dynamical system (LDS) is, with an unknown but fixed probability, replaced by noise. There, we present a robust method for the prediction of the outputs of the LDS and identification of the samples of noise, and prove guarantees on its statistical performance. One application lies in anomaly detection: the samples of noise, unlikely to have been generated by the dynamics, can be flagged to operators of the system for further study.
The Alan Turing Institute（艾伦·图灵研究所）；WMG Cyber Security Centre, University of Warwick（华威大学WMG网络安全中心）
The increasing connectivity of data and cyber-physical systems has resulted in a growing number of cyber-attacks. Real-time detection of such attacks, through the identification of anomalous activity, is required so that mitigation and contingent actions can be effectively and rapidly deployed. We propose a new approach for aggregating unsupervised anomaly detection algorithms and incorporating feedback when it becomes available. We apply this approach to open-source real datasets and show that both aggregating models, which we call experts, and incorporating feedback significantly improve the…
Massachusetts Institute of Technology（麻省理工学院）；Carnegie Mellon University（卡内基梅隆大学）
Inaccurate records of inventory occur frequently, and by some measures cost retailers approximately 4% in annual sales. Detecting inventory inaccuracies manually is cost-prohibitive, and existing algorithmic solutions rely almost exclusively on learning from longitudinal data, which is insufficient in the dynamic environment induced by modern retail operations. Instead, we propose a solution based on cross-sectional data over stores and SKUs, observing that detecting inventory inaccuracies can be viewed as a problem of identifying anomalies in a (low-rank) Poisson matrix. State-of-the-art appr…
Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition
King’s Communications, Learning & Information Processing (KCLIP) lab within the Centre for Intelligent Information Processing Systems (CIIPS), Department of Engineering, King’s College London（伦敦国王学院工程系智能信息处理系统中心（CIIPS）通信、学习与信息处理实验室（KCLIP））
Binghamton University, State University of New York（纽约州立大学宾汉姆顿分校）
Set-valued classification, a new classification paradigm that aims to identify all the plausible classes that an observation belongs to, can be obtained by learning the acceptance regions for all classes. Many existing set-valued classification methods do not consider the possibility that a new class that never appeared in the training data appears in the test data. Moreover, they are computationally expensive when the number of classes is large. We propose a Generalized Prediction Set (GPS) approach to estimate the acceptance regions while considering the possibility of a new class in the tes…
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）
The goal of anomaly detection is to identify anomalous samples from normal ones. In this paper, a small number of anomalies are assumed to be available at the training stage, but they are assumed to be collected only from several anomaly types, leaving the majority of anomaly types not represented in the collected anomaly dataset at all. To effectively leverage this kind of incomplete anomalous knowledge represented by the collected anomalies, we propose to learn a probability distribution that can not only model the normal samples, but also guarantee to assign low density values for the colle…
We consider the problem of finding anomalies in high-dimensional data using popular PCA based anomaly scores. The naive algorithms for computing these scores explicitly compute the PCA of the covariance matrix which uses space quadratic in the dimensionality of the data. We give the first streaming algorithms that use space that is linear or sublinear in the dimension. We prove general results showing that \emph{any} sketch of a matrix that satisfies a certain operator norm guarantee can be used to approximate these scores. We instantiate these results with powerful matrix sketching techniques…
Oak Ridge National Laboratory（橡树岭国家实验室）；North Carolina State University（北卡罗来纳州立大学）
This work presents a novel modeling and analysis framework for graph sequences which addresses the challenge of detecting and contextualizing anomalies in labelled, streaming graph data. We introduce a generalization of the BTER model of Seshadhri et al. by adding flexibility to community structure, and use this model to perform multi-scale graph anomaly detection. Specifically, probability models describing coarse subgraphs are built by aggregating probabilities at finer levels, and these closely related hierarchical models simultaneously detect deviations from expectation. This technique pro…
Yale University（耶鲁大学）；Mila -- Quebec AI Institute（米拉——魁北克人工智能研究所）
Anomaly detection is of great interest in fields where abnormalities need to be identified and corrected (e.g., medicine and finance). Deep learning methods for this task often rely on autoencoder reconstruction error, sometimes in conjunction with other errors. We show that this approach exhibits intrinsic biases that lead to undesirable results. Reconstruction-based methods are sensitive to training-data outliers and simple-to-reconstruct points. Instead, we introduce a new unsupervised Lipschitz anomaly discriminator that does not suffer from these biases. Our anomaly discriminator is train…
Shanghai Jiao Tong University（上海交通大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Surrogate task based methods have recently shown great promise for unsupervised image anomaly detection. However, there is no guarantee that the surrogate tasks share the consistent optimization direction with anomaly detection. In this paper, we return to a direct objective function for anomaly detection with information theory, which maximizes the distance between normal and anomalous data in terms of the joint distribution of images and their representation. Unfortunately, this objective function is not directly optimizable under the unsupervised setting where no anomalous data is provided …
Nearest-neighbor (NN) procedures are well studied and widely used in both supervised and unsupervised learning problems. In this paper we are concerned with investigating the performance of NN-based methods for anomaly detection. We first show through extensive simulations that NN methods compare favorably to some of the other state-of-the-art algorithms for anomaly detection based on a set of benchmark synthetic datasets. We further consider the performance of NN methods on real datasets, and relate it to the dimensionality of the problem. Next, we analyze the theoretical properties of NN-met…
Much of the world's data is streaming, time-series data, where anomalies give significant information in critical situations; examples abound in domains such as finance, IT, security, medical, and energy. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, not batches, and learn while simultaneously making predictions. There are no benchmarks to adequately test and score the efficacy of real-time anomaly detectors. Here we propose the Numenta Anomaly Benchmark (NAB), which attempts to provide a controlled and repeatable environment o…
Resonant Anomaly Detection with Multiple Reference Datasets
Stanford University（斯坦福大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Berkeley Institute for Data Science, University of California, Berkeley（加州大学伯克利分校伯克利数据科学研究所）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）
Applied AI Institute, Deakin University（迪肯大学应用人工智能研究所）
Temporal anomaly detection looks for irregularities over space-time. Unsupervised temporal models employed thus far typically work on sequences of feature vectors, and much less on temporal multiway data. We focus our investigation on two-way data, in which a data matrix is observed at each time step. Leveraging recent advances in matrix-native recurrent neural networks, we investigated strategies for data arrangement and unsupervised training for temporal multiway anomaly detection. These include compressing-decompressing, encoding-predicting, and temporal data differencing. We conducted a co…
The modern industrial environment is equipping myriads of smart manufacturing machines where the state of each device can be monitored continuously. Such monitoring can help identify possible future failures and develop a cost-effective maintenance plan. However, it is a daunting task to perform early detection with low false positives and negatives from the huge volume of collected data. This requires developing a holistic machine learning framework to address the issues in condition monitoring of high-priority components and develop efficient techniques to detect anomalies that can detect an…
Washington University in St. Louis（圣路易斯华盛顿大学）；Qatar University（卡塔尔大学）
Recently, advances in machine learning techniques have attracted the attention of the research community to build intrusion detection systems (IDS) that can detect anomalies in the network traffic. Most of the research works, however, do not differentiate among different types of attacks. This is, in fact, necessary for appropriate countermeasures and defense against attacks. In this paper, we investigate both detecting and categorizing anomalies rather than just detecting, which is a common trend in the contemporary research works. We have used a popular publicly available dataset to build an…
Avast Software（Avast软件公司）；Czech Technical University in Prague（布拉格捷克理工大学）
Anomaly detection is a method for discovering unusual and suspicious behavior. In many real-world scenarios, the examined events can be directly linked to the actions of an adversary, such as attacks on computer networks or frauds in financial operations. While the defender wants to discover such malicious behavior, the attacker seeks to accomplish their goal (e.g., exfiltrating data) while avoiding the detection. To this end, anomaly detectors have been used in a game-theoretic framework that captures these goals of a two-player competition. We extend the existing models to more realistic set…
In the era of Internet of Things (IoT), network-wide anomaly detection is a crucial part of monitoring IoT networks due to the inherent security vulnerabilities of most IoT devices. Principal Components Analysis (PCA) has been proposed to separate network traffics into two disjoint subspaces corresponding to normal and malicious behaviors for anomaly detection. However, the privacy concerns and limitations of devices' computing resources compromise the practical effectiveness of PCA. We propose a federated PCA-based Grassmannian optimization framework that coordinates IoT devices to aggregate …
Idiap Research Institute（伊迪亚普研究所）；École Polytéchnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院（EPFL））
Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker. Given how stealthy backdoor attacks are, consequences of these backdoors could be disastrous if such networks were to be deployed for applications as critical as border or access control. In this paper, we propose a novel backdoored network detection method based on the principle of anomaly detection, involving access to the clean part of the training data …
SHU-UTS SILC Business School, Shanghai University（上海大学悉尼工商学院）；SHU-SUCG Research Centre for Building Industrialization（上海建工集团建筑工业化研究中心）；Shanghai Tunnel Engineering Co., Ltd（上海隧道工程有限公司）
Time-series anomaly detection plays a vital role in monitoring complex operation conditions. However, the detection accuracy of existing approaches is heavily influenced by pattern distribution, existence of multiple normal patterns, dynamical features representation, and parameter settings. For the purpose of improving the robustness and guaranteeing the accuracy, this research combined the strengths of negative selection, unthresholded recurrence plots, and an extreme learning machine autoencoder and then proposed robust anomaly detection for time-series data (RADTD), which can automatically…
Machine Learning (ML) approaches have been used to enhance the detection capabilities of Network Intrusion Detection Systems (NIDSs). Recent work has achieved near-perfect performance by following binary- and multi-class network anomaly detection tasks. Such systems depend on the availability of both (benign and malicious) network data classes during the training phase. However, attack data samples are often challenging to collect in most organisations due to security controls preventing the penetration of known malicious traffic to their networks. Therefore, this paper proposes a Deep One-Cla…
Rhodes University（罗德斯大学）；African Institute for Mathematical Sciences（非洲数学科学研究所）；Ghana Space Science and Technology Institute（加纳空间科学技术研究所）；Ghana Atomic Energy Commission（加纳原子能委员会）；University of Ngaoundéré（恩冈代雷大学）；University of Ferrara（费拉拉大学）
One of the critical factors that drive the economic development of a country and guarantee the sustainability of its industries is the constant availability of electricity. This is usually provided by the national electric grid. However, in developing countries where companies are emerging on a constant basis including telecommunication industries, those are still experiencing a non-stable electricity supply. Therefore, they have to rely on generators to guarantee their full functionality. Those generators depend on fuel to function and the rate of consumption gets usually high, if not monitor…
Center for Applied Intelligent Systems Research (CAISR)（应用智能系统研究中心）；Halmstad University（哈尔姆斯塔德大学）
In contextual anomaly detection, an object is only considered anomalous within a specific context. Most existing methods for CAD use a single context based on a set of user-specified contextual features. However, identifying the right context can be very challenging in practice, especially in datasets, with a large number of attributes. Furthermore, in real-world systems, there might be multiple anomalies that occur in different contexts and, therefore, require a combination of several "useful" contexts to unveil them. In this work, we leverage active learning and ensembles to effectively dete…
In this paper, we present a memory-augmented algorithm for anomaly detection. Classical anomaly detection algorithms focus on learning to model and generate normal data, but typically guarantees for detecting anomalous data are weak. The proposed Memory Augmented Generative Adversarial Networks (MEMGAN) interacts with a memory module for both the encoding and generation processes. Our algorithm is such that most of the \textit{encoded} normal data are inside the convex hull of the memory units, while the abnormal data are isolated outside. Such a remarkable property leads to good (resp.\ poor)…
This paper studies theoretically and empirically a method of turning machine-learning algorithms into probabilistic predictors that automatically enjoys a property of validity (perfect calibration) and is computationally efficient. The price to pay for perfect calibration is that these probabilistic predictors produce imprecise (in practice, almost precise for large data sets) probabilities. When these imprecise probabilities are merged into precise probabilities, the resulting predictors, while losing the theoretical property of perfect calibration, are consistently more accurate than the exi…
In this paper, we investigate algorithms for anomaly detection. Previous anomaly detection methods focus on modeling the distribution of non-anomalous data provided during training. However, this does not necessarily ensure the correct detection of anomalous data. We propose a new Regularized Cycle Consistent Generative Adversarial Network (RCGAN) in which deep neural networks are adversarially trained to better recognize anomalous samples. This approach is based on leveraging a penalty distribution with a new definition of the loss function and novel use of discriminator networks. It is based…
California Institute of Technology（加州理工学院）；Hebrew University of Jerusalem（希伯来大学）；Ben-Gurion University（本-古里安大学）；Harvard University（哈佛大学）；University of Pennsylvania（宾夕法尼亚大学）
The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in isolation, the guarantee need not hold if the algorithms are composed adaptively. In this paper, we study three notions of generalization---increasing in strength---that are robust to postprocessing and amenable to adaptive composition, and examine the relationships between them. We call the weakest such notion Robust Generalization. A second, intermediate, no…
Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）；Cyber Security CRC（网络安全合作研究中心）；Illinois Institute of Technology（伊利诺伊理工学院）；Concordia University（康考迪亚大学）；Hong Kong Polytechnic University（香港理工大学）；Ericsson Security Research, Ericsson Canada（加拿大爱立信公司爱立信安全研究院）；University of Connecticut（康涅狄格大学）
Outsourcing anomaly detection to third-parties can allow data owners to overcome resource constraints (e.g., in lightweight IoT devices), facilitate collaborative analysis (e.g., under distributed or multi-party scenarios), and benefit from lower costs and specialized expertise (e.g., of Managed Security Service Providers). Despite such benefits, a data owner may feel reluctant to outsource anomaly detection without sufficient privacy protection. To that end, most existing privacy solutions would face a novel challenge, i.e., preserving privacy usually requires the difference between data entr…
Anomaly Correction of Business Processes Using Transformer Autoencoder
Anhui University of Science and Technology（安徽理工大学）；Anhui Province Engineering Laboratory for Big Data Analysis and Early Warning Technology of Coal Mine Safety（安徽省煤矿安全大数据分析与预警技术工程实验室）
