English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Anomaly detection plays an important role in modern data-driven securityapplications, such as detecting suspicious access to a socket from a process.In many cases, such events can be described as a collection of categoricalvalues that are considered as entities of different types, which we callheterogeneous categorical events. Due to the lack of intrinsic distancemeasures among entities, and the exponentially large event space, most existingwork relies heavily on heuristics to calculate abnormal scores for events.Different from previous work, we propose a principled and unified probabilisticmodel APE (Anomaly detection via Probabilistic pairwise interaction and Entityembedding) that directly models the likelihood of events. In this model, weembed entities into a common latent space using their observed co-occurrence indifferent events. More specifically, we first model the compatibility of eachpair of entities according to their embeddings. Then we utilize the weightedpairwise interactions of different entity types to define the eventprobability. Using Noise-Contrastive Estimation with "context-dependent" noisedistribution, our model can be learned efficiently regardless of the largeevent space. Experimental results on real enterprise surveillance data showthat our methods can accurately detect abnormal events compared to otherstate-of-the-art abnormal detection techniques.

Entity Embedding-based Anomaly Detection for Heterogeneous Categorical Events