CLAIOct 15, 2021

Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm

arXiv:2110.08036v14 citations
AI Analysis

This addresses the problem of high computational cost in generating adversarial examples for NLP models, offering a more efficient solution for researchers and practitioners, though it is an incremental improvement in attack methods.

The paper tackles the inefficiency of existing text adversarial attack methods by proposing a novel model that achieves a 100% attack success rate on BERT and BiLSTM on IMDB while reducing queries to 1/4 and 1/6.5 of the state-of-the-art method, respectively.

The research of adversarial attacks in the text domain attracts many interests in the last few years, and many methods with a high attack success rate have been proposed. However, these attack methods are inefficient as they require lots of queries for the victim model when crafting text adversarial examples. In this paper, a novel attack model is proposed, its attack success rate surpasses the benchmark attack methods, but more importantly, its attack efficiency is much higher than the benchmark attack methods. The novel method is empirically evaluated by attacking WordCNN, LSTM, BiLSTM, and BERT on four benchmark datasets. For instance, it achieves a 100\% attack success rate higher than the state-of-the-art method when attacking BERT and BiLSTM on IMDB, but the number of queries for the victim models only is 1/4 and 1/6.5 of the state-of-the-art method, respectively. Also, further experiments show the novel method has a good transferability on the generated adversarial examples.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes