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

Neural ranking models (NRMs) have undergone significant development and havebecome integral components of information retrieval (IR) systems.Unfortunately, recent research has unveiled the vulnerability of NRMs toadversarial document manipulations, potentially exploited by malicious searchengine optimization practitioners. While progress in adversarial attackstrategies aids in identifying the potential weaknesses of NRMs before theirdeployment, the defensive measures against such attacks, like the detection ofadversarial documents, remain inadequately explored. To mitigate this gap, thispaper establishes a benchmark dataset to facilitate the investigation ofadversarial ranking defense and introduces two types of detection tasks foradversarial documents. A comprehensive investigation of the performance ofseveral detection baselines is conducted, which involve examining thespamicity, perplexity, and linguistic acceptability, and utilizing supervisedclassifiers. Experimental results demonstrate that a supervised classifier caneffectively mitigate known attacks, but it performs poorly against unseenattacks. Furthermore, such classifier should avoid using query text to preventlearning the classification on relevance, as it might lead to the inadvertentdiscarding of relevant documents.

Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection