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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

While modern day web applications aim to create impact at the civilizationlevel, they have become vulnerable to adversarial activity, where the nextcyber-attack can take any shape and can originate from anywhere. The increasingscale and sophistication of attacks, has prompted the need for a data drivensolution, with machine learning forming the core of many cybersecurity systems.Machine learning was not designed with security in mind, and the essentialassumption of stationarity, requiring that the training and testing data followsimilar distributions, is violated in an adversarial domain. In this paper, anadversary's view point of a classification based system, is presented. Based ona formal adversarial model, the Seed-Explore-Exploit framework is presented,for simulating the generation of data driven and reverse engineering attacks onclassifiers. Experimental evaluation, on 10 real world datasets and using theGoogle Cloud Prediction Platform, demonstrates the innate vulnerability ofclassifiers and the ease with which evasion can be carried out, without anyexplicit information about the classifier type, the training data or theapplication domain. The proposed framework, algorithms and empiricalevaluation, serve as a white hat analysis of the vulnerabilities, and aim tofoster the development of secure machine learning frameworks.

Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains