Goto

Collaborating Authors

Results


Whiteboard Blog Series: AI for IT and Anomaly Detection in Networks

#artificialintelligence

Every network is different yet comprised of similar components. We all use the same protocols but our user, application and device fingerprints are unique to each and every organization. This constitutes a big challenge for anomaly detection performed by a widely deployed platform. No single model fits all. The fundamental question is then, what is anomalous?


Visualizing Principal Components for Images - Hi! I am Nagdev

#artificialintelligence

Principal Component Analysis (PCA) is a great tool for a data analysis projects for a lot of reasons. If you have never heard of PCA, in simple words it does a linear transformation of your features using covariance or correlation. I will add a few links below if you want to know more about it. Some of the applications of PCA are dimensional reduction, feature analysis, data compression, anomaly detection, clustering and many more. The first time I learnt about PCA, it was not easy to understand and quite confusing.


An Interactive Visualization of Autoencoders, Built with Tensorflow.js

#artificialintelligence

Introducing Anomagram - An interactive tool that lets you train and evaluate an autoencoder for the task of anomaly detection on ECG data. Across many business use cases that generate data, it is frequently desirable to automatically identify data samples that deviate from "normal". In many cases, these deviations are indicative of issues that need to be addressed. For example, an abnormally high cash withdrawal from a previously unseen location may be indicative of fraud. An abnormally high CPU temperature may be indicative of impending hardware failure.


IoT Anomaly detection - algorithms, techniques and open source implementation

#artificialintelligence

Learning classifiers for misuse and anomaly detection using a bag of system calls representation. Anomaly detection in health data based on deep learning. Abnormal human activity recognition using SVM based approach. Anomaly detection of gas turbines based on normal pattern extraction. Contextual anomaly detection for a critical industrial system based on logs and metrics.


Machine Learning in the Elastic Stack

#artificialintelligence

Machine Learning helps to automate analysis and surface insights that are important for the day-to-day operation of certain business functions. In this talk, Elvis Saravia, Education Architect at Elastic, will focus on introducing a series of machine learning jobs, via the Machine Learning UI, that are easy to compose and can help classify new information (in the form of document classification) and help reveal an abnormal behavior in the data (in the form of anomaly detection).


How machine learning finds anomalies to catch financial cybercriminals

#artificialintelligence

In the last few months, millions of dollars have been stolen from unemployment systems during this time of immense pressure due to coronavirus-related claims. A skilled ring of international fraudsters has been submitting false unemployment claims for individuals that still have steady work. The attackers use previously acquired Personally Identifiable Information (PII) such as social security numbers, addresses, names, phone numbers, and banking account information to trick public officials into accepting the claims. Payouts to these employed people are then redirected to money laundering accomplices who pass the money around to veil the illicit nature of the cash before depositing it into their own accounts. The acquisition of the PII that enabled these attacks, and the pattern of money laundering that financial institutions failed to detect highlight the importance of renewed security.


How machine learning combats financial cybercrime

#artificialintelligence

In the last few months, millions of dollars have been stolen from unemployment systems during this time of immense pressure due to coronavirus-related claims. A skilled ring of international fraudsters has been submitting false unemployment claims for individuals that still have steady work. The attackers use previously acquired Personally Identifiable Information (PII) such as social security numbers, addresses, names, phone numbers, and banking account information to trick public officials into accepting the claims. Payouts to these employed people are then redirected to money laundering accomplices who pass the money around to veil the illicit nature of the cash before depositing it into their own accounts. The acquisition of the PII that enabled these attacks, and the pattern of money laundering that financial institutions failed to detect highlight the importance of renewed security.


Outlier Detection -- Theory, Visualizations, and Code

#artificialintelligence

Outlier Detection is also known as anomaly detection, noise detection, deviation detection, or exception mining. There is no universally accepted definition. An early definition by (Grubbs, 1969) is: An outlying observation, or outlier, is one that appears to deviate markedly from other members of the sample in which it occurs. An observation which appears to be inconsistent with the remainder of that set of data. A list of applications that utilize outlier detection according to (Hodge, V.J. and Austin, J., 2014) is: This is analogous to unsupervised clustering.


Using Machine Learning for Threat Detection - Security Boulevard

#artificialintelligence

We all live by rules, some rules are defined strictly and some loosely. There is new research in social psychology about how our world is wired by rule makers & rule breakers¹, including how all of us as people and communities are wired to follow some rules'tightly', and some'loosely'. Cybersecurity is eventually about people, and how some break rules (attackers) and others make rules (Cyber Warriors & products). The cybersecurity effort at the very heart of it is a pattern recognition problem, trying to understand patterns of attacks in various ways and classifying them into benign (rule follower), malicious (rule breaker), or potentially requiring more investigation on precise intent. So, what is the role of Machine Learning (ML) in such pattern recognition problems?


Predictive Maintenance with Machine Learning on Oracle Database 20c

#artificialintelligence

According to McKinsey's study "Visualizing the uses and potential impact of AI and other analytics", 2018, the estimated impact of artificial intelligence and other analytics on all industries regarding anomaly detection is between $1.0T and $1.4T. Anomaly detection is the critical success factor in predictive maintenance, which tries to anticipate when maintenance is required. This differs from the classical preventive approach, in which activities are planned on a regularly scheduled basis, or condition-based maintenance activities, in which assets are monitored through IoT sensors. Applying anomaly detection algorithms based on machine learning, it's possible to perform prognostics to estimate the condition of a system or a component and its remaining useful life (RUL), in order to predict an incoming failure. One of the most famous algorithms is the MSET-SPRT, well-described with a use case in this blog post: "Machine Learning Use Case: Real-Time Support for Engineered Systems."