Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm
Zhao, Tengfei, Ge, Zhaocheng, Hu, Hanping, Shi, Dingmeng
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-15-2021
- Country:
- South America > Brazil
- North America
- United States
- Washington > King County
- Seattle (0.04)
- Oregon > Multnomah County
- Portland (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- San Francisco County > San Francisco (0.14)
- San Diego County > San Diego (0.04)
- Monterey County > Monterey (0.04)
- Santa Clara County
- Washington > King County
- Canada
- Quebec > Montreal (0.04)
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- United States
- Europe
- Asia > Middle East
- Genre:
- Research Report > Promising Solution (0.94)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: