Difference between revisions of "Anomaly Detection"
(Created page with "[http://www.youtube.com/results?search_query=cyber+security+anomaly+detection+defense+ai+artificial+intelligence Youtube search...] * Cybersecurity ** Cybersecurity Ref...") |
|||
| Line 4: | Line 4: | ||
** [[Cybersecurity References]] | ** [[Cybersecurity References]] | ||
** [[Offense - Adversarial Threats/Attacks]] | ** [[Offense - Adversarial Threats/Attacks]] | ||
| + | * [[...find outliers]] | ||
* [[Government Services]] | * [[Government Services]] | ||
* [[Capabilities]] | * [[Capabilities]] | ||
| Line 17: | Line 18: | ||
<youtube>yZ-Y1WCM0lc</youtube> | <youtube>yZ-Y1WCM0lc</youtube> | ||
<youtube>fRklX97iGIw</youtube> | <youtube>fRklX97iGIw</youtube> | ||
| + | |||
| + | == [[Principal Component Analysis (PCA)]] Anomaly Detection == | ||
| + | [http://www.youtube.com/results?search_query=Principal+Components+Analysis+PCA+Anomaly+Detection+Outliers YouTube search...] | ||
| + | |||
| + | * [http://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/pca-based-anomaly-detection PCA-Based Anomaly Detection | Microsoft] | ||
| + | |||
| + | PCA-based anomaly detection - the vast majority of the data falls into a stereotypical distribution; points deviating dramatically from that distribution are suspect [http://www.linkedin.com/pulse/part-2-keep-simple-machine-learning-algorithms-big-dr-dinesh/ Keep it Simple : Machine Learning & Algorithms for Big Boys | Dinesh Chandrasekar] | ||
| + | |||
| + | http://doi.ieeecomputersociety.org/cms/Computer.org/dl/trans/tk/2013/07/figures/ttk20130714602.gif | ||
| + | |||
| + | <youtube>hxGF7cPvs_c</youtube> | ||
| + | <youtube>ExoAbXPJ7NQ</youtube> | ||
| + | <youtube>UEPFCp5WpIY</youtube> | ||
| + | <youtube>6lc6Oz0k9WA</youtube> | ||
Revision as of 08:05, 29 July 2018
- Cybersecurity
- ...find outliers
- Government Services
- Capabilities
- Defenses Against Adversarial Examples for Deep Neural Networks
______________________________________________________
Principal Component Analysis (PCA) Anomaly Detection
PCA-based anomaly detection - the vast majority of the data falls into a stereotypical distribution; points deviating dramatically from that distribution are suspect Keep it Simple : Machine Learning & Algorithms for Big Boys | Dinesh Chandrasekar
