AdvCodeMix: Adversarial Attack on Code-Mixed Data

10/30/2021
by   Sourya Dipta Das, et al.
0

Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have explained the first generalized framework on text perturbation to attack code-mixed classification models in a black-box setting. We rely on various perturbation techniques that preserve the semantic structures of the sentences and also obscure the attacks from the perception of a human user. The present methodology leverages the importance of a token to decide where to attack by employing various perturbation strategies. We test our strategies on various sentiment classification models trained on Bengali-English and Hindi-English code-mixed datasets, and reduce their F1-scores by nearly 51 and 53 tokens are perturbed in a given sentence.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset