BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces
This addresses the vulnerability of NLP models to adversarial attacks, offering a more efficient method for crafting high-quality examples, though it is incremental as it builds on existing word-level attack strategies.
The paper tackles the problem of generating textual adversarial examples in black-box settings by proposing BeamAttack, which uses mixed semantic spaces and improved beam search to achieve higher attack success rates and reduce query/time costs, e.g., improving attack success by up to 7% and saving up to 85% queries compared to baselines.
Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting, attacker can fool the model without knowing model's parameters and architecture. Previous works on word-level attacks widely use single semantic space and greedy search as a search strategy. However, these methods fail to balance the attack success rate, quality of adversarial examples and time consumption. In this paper, we propose BeamAttack, a textual attack algorithm that makes use of mixed semantic spaces and improved beam search to craft high-quality adversarial examples. Extensive experiments demonstrate that BeamAttack can improve attack success rate while saving numerous queries and time, e.g., improving at most 7\% attack success rate than greedy search when attacking the examples from MR dataset. Compared with heuristic search, BeamAttack can save at most 85\% model queries and achieve a competitive attack success rate. The adversarial examples crafted by BeamAttack are highly transferable and can effectively improve model's robustness during adversarial training. Code is available at https://github.com/zhuhai-ustc/beamattack/tree/master