Related papers: Universal Data Anomaly Detection via Inverse Gener…
Methods of performing anomaly detection on high-dimensional data sets are needed, since algorithms which are trained on data are only expected to perform well on data that is similar to the training data. There are theoretical results on…
Deep Neural Networks (DNNs) have been shown vulnerable to Test-Time Evasion attacks (TTEs, or adversarial examples), which, by making small changes to the input, alter the DNN's decision. We propose an unsupervised attack detector on DNN…
Anomaly detection is the process of finding data points that deviate from a baseline. In a real-life setting, anomalies are usually unknown or extremely rare. Moreover, the detection must be accomplished in a timely manner or the risk of…
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications. However, existing adversarial detection methods require access to sufficient training data, which brings…
Current approaches to novelty or anomaly detection are based on deep neural networks. Despite their effectiveness, neural networks are also vulnerable to imperceptible deformations of the input data. This is a serious issue in critical…
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging. Models are typically based on large amounts of data with annotated examples of known markers aiming at automating…
Anomaly detection, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-based methods were shown to achieve superior results on this…
Given high-dimensional time series data (e.g., sensor data), how can we detect anomalous events, such as system faults and attacks? More challengingly, how can we do this in a way that captures complex inter-sensor relationships, and…
Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such…
Anomaly detection is a task that recognizes whether an input sample is included in the distribution of a target normal class or an anomaly class. Conventional generative adversarial network (GAN)-based methods utilize an entire image…
Many anomaly detection approaches, especially deep learning methods, have been recently developed to identify abnormal image morphology by only employing normal images during training. Unfortunately, many prior anomaly detection methods…
Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging training sets. Previous work primarily focused on data…
Semi-supervised and unsupervised Generative Adversarial Networks (GAN)-based methods have been gaining popularity in anomaly detection task recently. However, GAN training is somewhat challenging and unstable. Inspired from previous work in…
We present a simple framework for one-class classification and anomaly detection. The core idea is to learn a mapping to transform the unknown distribution of training (normal) data to a known target distribution. Crucially, the target…
In anomaly detection, a prominent task is to induce a model to identify anomalies learned solely based on normal data. Generally, one is interested in finding an anomaly detector that correctly identifies anomalies, i.e., data points that…
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous…
Anomaly detection aims to detect data that do not conform to regular patterns, and such data is also called outliers. The anomalies to be detected are often tiny in proportion, containing crucial information, and are suitable for…
Acoustic anomaly detection aims at distinguishing abnormal acoustic signals from the normal ones. It suffers from the class imbalance issue and the lacking in the abnormal instances. In addition, collecting all kinds of abnormal or unknown…
Anomaly detection in complex domains poses significant challenges due to the need for extensive labeled data and the inherently imbalanced nature of anomalous versus benign samples. Graph-based machine learning models have emerged as a…
We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning is extended to the case for which one has access to an…