Issue #134 – A Targeted Attack on Black-Box Neural MT
10 Jun21
Issue #134 – A Targeted Attack on Black-Box Neural MT
Author: Dr. Karin Sim, Machine Translation Scientist @ Iconic
Introduction
Last week we looked at how neural machine translation (NMT) systems are naturally susceptible to gender bias. In today’s blog post we look at the vulnerability of an NMT system to targeted attacks, which could result in unsolicited or harmful translations. Specifically we report on work by Xu et al., 2021, which examines attacks on black-box NMT systems, where the internals of the system are unavailable to the attacker (such as secured commercial systems). They investigate how susceptible various NMT systems are, and what can be done to mitigate