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

Machine Learning-as-a-Service systems (MLaaS) have been largely developed forcybersecurity-critical applications, such as detecting network intrusions andfake news campaigns. Despite effectiveness, their robustness againstadversarial attacks is one of the key trust concerns for MLaaS deployment. Weare thus motivated to assess the adversarial robustness of the Machine Learningmodels residing at the core of these security-critical applications withcategorical inputs. Previous research efforts on accessing model robustnessagainst manipulation of categorical inputs are specific to use cases andheavily depend on domain knowledge, or require white-box access to the targetML model. Such limitations prevent the robustness assessment from being as adomain-agnostic service provided to various real-world applications. We proposea provably optimal yet computationally highly efficient adversarial robustnessassessment protocol for a wide band of ML-driven cybersecurity-criticalapplications. We demonstrate the use of the domain-agnostic robustnessassessment method with substantial experimental study on fake news detectionand intrusion detection problems.

AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs