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 machine translation systems are known to be vulnerable to adversarialtest inputs, however, as we show in this paper, these systems are alsovulnerable to training attacks. Specifically, we propose a poisoning attack inwhich a malicious adversary inserts a small poisoned sample of monolingual textinto the training set of a system trained using back-translation. This sampleis designed to induce a specific, targeted translation behaviour, such aspeddling misinformation. We present two methods for crafting poisoned examples,and show that only a tiny handful of instances, amounting to only 0.02% of thetraining set, is sufficient to enact a successful attack. We outline a defencemethod against said attacks, which partly ameliorates the problem. However, westress that this is a blind-spot in modern NMT, demanding immediate attention.

Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning